Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2352 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 13.2033. Min Range: -13.2033
Max Act: 13.2033. Min Act: -0.1700
Data Index: 4835838 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.2033. Min Range: -13.2033
Max Act: 13.0158. Min Act: -0.1700
Data Index: 1613110 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.2033. Min Range: -13.2033
Max Act: 13.0158. Min Act: -0.1700
Data Index: 7109816 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.2033. Min Range: -13.2033
Max Act: 13.0158. Min Act: -0.1700
Data Index: 4620189 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.2033. Min Range: -13.2033
Max Act: 12.9533. Min Act: -0.1700
Data Index: 248022 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.2033. Min Range: -13.2033
Max Act: 12.5783. Min Act: -0.1700
Data Index: 7109811 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.2033. Min Range: -13.2033
Max Act: 12.5783. Min Act: -0.1700
Data Index: 7109829 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.2033. Min Range: -13.2033
Max Act: 12.6408. Min Act: -0.1700
Data Index: 6517268 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.2033. Min Range: -13.2033
Max Act: 12.4533. Min Act: -0.1700
Data Index: 5187385 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.2033. Min Range: -13.2033
Max Act: 12.4533. Min Act: -0.1700
Data Index: 7109812 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.2033. Min Range: -13.2033
Max Act: 12.5158. Min Act: -0.1700
Data Index: 6272275 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.2033. Min Range: -13.2033
Max Act: 12.3908. Min Act: -0.1700
Data Index: 7109823 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.2033. Min Range: -13.2033
Max Act: 12.3283. Min Act: -0.1700
Data Index: 6874580 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.2033. Min Range: -13.2033
Max Act: 12.2658. Min Act: -0.1700
Data Index: 6272277 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.2033. Min Range: -13.2033
Max Act: 12.3283. Min Act: -0.1700
Data Index: 8240417 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.2033. Min Range: -13.2033
Max Act: 12.2658. Min Act: -0.1700
Data Index: 3772589 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.2033. Min Range: -13.2033
Max Act: 12.3283. Min Act: -0.1700
Data Index: 2256736 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.2033. Min Range: -13.2033
Max Act: 12.2033. Min Act: -0.1700
Data Index: 2375994 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.2033. Min Range: -13.2033
Max Act: 12.2033. Min Act: -0.1700
Data Index: 248021 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.2033. Min Range: -13.2033
Max Act: 12.2033. Min Act: -0.1700
Data Index: 2438039 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19