Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3007 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1388. Min Range: -10.1388
Max Act: 10.1388. Min Act: -0.1700
Data Index: 3490507 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1388. Min Range: -10.1388
Max Act: 9.7638. Min Act: -0.1700
Data Index: 829437 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1388. Min Range: -10.1388
Max Act: 9.7638. Min Act: -0.1700
Data Index: 2922905 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1388. Min Range: -10.1388
Max Act: 9.7013. Min Act: -0.1700
Data Index: 4231729 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1388. Min Range: -10.1388
Max Act: 9.6388. Min Act: -0.1700
Data Index: 7020269 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1388. Min Range: -10.1388
Max Act: 9.6388. Min Act: -0.1700
Data Index: 2603074 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1388. Min Range: -10.1388
Max Act: 9.5763. Min Act: -0.1700
Data Index: 7020271 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1388. Min Range: -10.1388
Max Act: 9.5763. Min Act: -0.1700
Data Index: 2503469 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1388. Min Range: -10.1388
Max Act: 9.5763. Min Act: -0.1700
Data Index: 6296823 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1388. Min Range: -10.1388
Max Act: 9.5763. Min Act: -0.1700
Data Index: 4375381 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1388. Min Range: -10.1388
Max Act: 9.5763. Min Act: -0.1700
Data Index: 5103038 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1388. Min Range: -10.1388
Max Act: 9.5138. Min Act: -0.1700
Data Index: 1946524 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1388. Min Range: -10.1388
Max Act: 9.5138. Min Act: -0.1700
Data Index: 3337675 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1388. Min Range: -10.1388
Max Act: 9.5138. Min Act: -0.1700
Data Index: 893739 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1388. Min Range: -10.1388
Max Act: 9.5138. Min Act: -0.1700
Data Index: 6644448 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1388. Min Range: -10.1388
Max Act: 9.5138. Min Act: -0.1700
Data Index: 1198722 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1388. Min Range: -10.1388
Max Act: 9.5138. Min Act: -0.1700
Data Index: 2848843 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1388. Min Range: -10.1388
Max Act: 9.5138. Min Act: -0.1700
Data Index: 4104155 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1388. Min Range: -10.1388
Max Act: 9.5138. Min Act: -0.1700
Data Index: 3443565 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1388. Min Range: -10.1388
Max Act: 9.4513. Min Act: -0.1700
Data Index: 259086 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19