Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3942 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1152. Min Range: -8.1152
Max Act: 8.1152. Min Act: -0.1700
Data Index: 6169841 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1152. Min Range: -8.1152
Max Act: 7.7715. Min Act: -0.1700
Data Index: 7833762 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1152. Min Range: -8.1152
Max Act: 7.6152. Min Act: -0.1700
Data Index: 2498611 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1152. Min Range: -8.1152
Max Act: 7.6152. Min Act: -0.1700
Data Index: 4395670 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1152. Min Range: -8.1152
Max Act: 7.5527. Min Act: -0.1700
Data Index: 586475 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1152. Min Range: -8.1152
Max Act: 7.4902. Min Act: -0.1700
Data Index: 5185791 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1152. Min Range: -8.1152
Max Act: 7.4902. Min Act: -0.1700
Data Index: 6537001 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1152. Min Range: -8.1152
Max Act: 7.4590. Min Act: -0.1700
Data Index: 673076 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1152. Min Range: -8.1152
Max Act: 7.4277. Min Act: -0.1700
Data Index: 2617176 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1152. Min Range: -8.1152
Max Act: 7.3965. Min Act: -0.1700
Data Index: 3455464 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1152. Min Range: -8.1152
Max Act: 7.3652. Min Act: -0.1700
Data Index: 7819362 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1152. Min Range: -8.1152
Max Act: 7.3340. Min Act: -0.1700
Data Index: 271434 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1152. Min Range: -8.1152
Max Act: 7.3652. Min Act: -0.1700
Data Index: 943671 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1152. Min Range: -8.1152
Max Act: 7.3340. Min Act: -0.1700
Data Index: 1334438 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1152. Min Range: -8.1152
Max Act: 7.3027. Min Act: -0.1700
Data Index: 6399792 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1152. Min Range: -8.1152
Max Act: 7.3652. Min Act: -0.1700
Data Index: 7256420 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1152. Min Range: -8.1152
Max Act: 7.3027. Min Act: -0.1700
Data Index: 8384634 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1152. Min Range: -8.1152
Max Act: 7.3340. Min Act: -0.1700
Data Index: 1060672 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1152. Min Range: -8.1152
Max Act: 7.3027. Min Act: -0.1700
Data Index: 8210054 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1152. Min Range: -8.1152
Max Act: 7.2090. Min Act: -0.1700
Data Index: 7175066 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19