Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3546 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.4344. Min Act: -0.1700
Data Index: 1087172 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.4032. Min Act: -0.1700
Data Index: 1204564 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.3094. Min Act: -0.1700
Data Index: 8778153 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.2469. Min Act: -0.1700
Data Index: 6849976 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.2469. Min Act: -0.1700
Data Index: 3181863 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.2469. Min Act: -0.1700
Data Index: 6295493 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.2469. Min Act: -0.1700
Data Index: 1776424 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.2157. Min Act: -0.1700
Data Index: 3444059 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.1844. Min Act: -0.1700
Data Index: 4132070 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.1532. Min Act: -0.1700
Data Index: 6787274 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.1532. Min Act: -0.1700
Data Index: 3537835 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.1219. Min Act: -0.1700
Data Index: 6239880 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.1219. Min Act: -0.1700
Data Index: 7298672 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.1219. Min Act: -0.1700
Data Index: 8450933 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.1219. Min Act: -0.1700
Data Index: 2105591 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.1219. Min Act: -0.1700
Data Index: 3177232 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.1219. Min Act: -0.1700
Data Index: 1144667 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.1219. Min Act: -0.1700
Data Index: 4485064 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.1219. Min Act: -0.1700
Data Index: 7647240 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4344. Min Range: -5.4344
Max Act: 5.0907. Min Act: -0.1700
Data Index: 5800513 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19