Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 400 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7210. Min Range: -6.7210
Max Act: 6.7210. Min Act: -0.1700
Data Index: 6576119 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7210. Min Range: -6.7210
Max Act: 6.3147. Min Act: -0.1700
Data Index: 7823115 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7210. Min Range: -6.7210
Max Act: 6.1897. Min Act: -0.1700
Data Index: 6106687 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7210. Min Range: -6.7210
Max Act: 6.1897. Min Act: -0.1700
Data Index: 478024 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7210. Min Range: -6.7210
Max Act: 6.1585. Min Act: -0.1700
Data Index: 2490765 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7210. Min Range: -6.7210
Max Act: 6.1272. Min Act: -0.1700
Data Index: 1219365 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7210. Min Range: -6.7210
Max Act: 6.0960. Min Act: -0.1700
Data Index: 5260174 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7210. Min Range: -6.7210
Max Act: 6.0960. Min Act: -0.1700
Data Index: 6537499 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7210. Min Range: -6.7210
Max Act: 5.9397. Min Act: -0.1700
Data Index: 7232415 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7210. Min Range: -6.7210
Max Act: 5.9710. Min Act: -0.1700
Data Index: 598784 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7210. Min Range: -6.7210
Max Act: 5.9397. Min Act: -0.1700
Data Index: 177525 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7210. Min Range: -6.7210
Max Act: 5.9710. Min Act: -0.1700
Data Index: 2785885 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7210. Min Range: -6.7210
Max Act: 5.9397. Min Act: -0.1700
Data Index: 1270547 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7210. Min Range: -6.7210
Max Act: 5.9085. Min Act: -0.1700
Data Index: 8110154 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7210. Min Range: -6.7210
Max Act: 5.9085. Min Act: -0.1700
Data Index: 3353146 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7210. Min Range: -6.7210
Max Act: 5.8772. Min Act: -0.1700
Data Index: 187703 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7210. Min Range: -6.7210
Max Act: 5.8460. Min Act: -0.1700
Data Index: 78788 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7210. Min Range: -6.7210
Max Act: 5.8460. Min Act: -0.1700
Data Index: 6098518 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7210. Min Range: -6.7210
Max Act: 5.8460. Min Act: -0.1700
Data Index: 1246421 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7210. Min Range: -6.7210
Max Act: 5.8147. Min Act: -0.1700
Data Index: 5419757 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19