Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1815 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.7091. Min Act: -0.1700
Data Index: 6254280 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.5528. Min Act: -0.1700
Data Index: 5627906 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.5216. Min Act: -0.1700
Data Index: 4478397 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.5216. Min Act: -0.1700
Data Index: 7739344 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.5216. Min Act: -0.1700
Data Index: 907185 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.4903. Min Act: -0.1700
Data Index: 2711153 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.4903. Min Act: -0.1699
Data Index: 5866354 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.5216. Min Act: -0.1700
Data Index: 8439085 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.4903. Min Act: -0.1700
Data Index: 2608962 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.4903. Min Act: -0.1700
Data Index: 1564155 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.4903. Min Act: -0.1700
Data Index: 496630 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.4591. Min Act: -0.1700
Data Index: 677146 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.4591. Min Act: -0.1700
Data Index: 461378 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.4278. Min Act: -0.1700
Data Index: 3638175 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.4591. Min Act: -0.1700
Data Index: 8425130 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.4591. Min Act: -0.1700
Data Index: 5552129 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.4591. Min Act: -0.1700
Data Index: 3646065 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.4591. Min Act: -0.1700
Data Index: 5890624 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.4591. Min Act: -0.1700
Data Index: 4261440 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.4591. Min Act: -0.1700
Data Index: 8644943 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19