Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3358 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.6664. Min Act: -0.1700
Data Index: 5653794 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.6664. Min Act: -0.1700
Data Index: 8698962 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.4789. Min Act: -0.1700
Data Index: 4943619 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.4164. Min Act: -0.1700
Data Index: 5702055 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.4164. Min Act: -0.1700
Data Index: 1031664 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.4164. Min Act: -0.1700
Data Index: 4622881 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.4164. Min Act: -0.1700
Data Index: 8624112 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.4164. Min Act: -0.1700
Data Index: 4471467 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.4164. Min Act: -0.1700
Data Index: 505085 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.3539. Min Act: -0.1700
Data Index: 6520115 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.3539. Min Act: -0.1700
Data Index: 233372 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.2914. Min Act: -0.1700
Data Index: 565707 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.2289. Min Act: -0.1700
Data Index: 4431806 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.3539. Min Act: -0.1700
Data Index: 6237871 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.2914. Min Act: -0.1700
Data Index: 1296828 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.2289. Min Act: -0.1700
Data Index: 6194024 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.2289. Min Act: -0.1700
Data Index: 8082669 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.2289. Min Act: -0.1700
Data Index: 5676293 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.1664. Min Act: -0.1700
Data Index: 6457207 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6664. Min Range: -8.6664
Max Act: 8.1664. Min Act: -0.1700
Data Index: 5809964 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19