Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3526 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6272. Min Range: -10.6272
Max Act: 10.6272. Min Act: -0.1700
Data Index: 5683815 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6272. Min Range: -10.6272
Max Act: 10.4397. Min Act: -0.1700
Data Index: 4959864 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6272. Min Range: -10.6272
Max Act: 10.3147. Min Act: -0.1700
Data Index: 4212706 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6272. Min Range: -10.6272
Max Act: 10.1272. Min Act: -0.1700
Data Index: 5700242 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6272. Min Range: -10.6272
Max Act: 10.0647. Min Act: -0.1700
Data Index: 8717847 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6272. Min Range: -10.6272
Max Act: 10.1272. Min Act: -0.1700
Data Index: 766027 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6272. Min Range: -10.6272
Max Act: 10.0022. Min Act: -0.1700
Data Index: 7923653 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6272. Min Range: -10.6272
Max Act: 9.9397. Min Act: -0.1700
Data Index: 8317891 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6272. Min Range: -10.6272
Max Act: 9.8772. Min Act: -0.1700
Data Index: 570196 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6272. Min Range: -10.6272
Max Act: 9.8147. Min Act: -0.1700
Data Index: 557348 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6272. Min Range: -10.6272
Max Act: 9.8147. Min Act: -0.1700
Data Index: 7916027 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6272. Min Range: -10.6272
Max Act: 9.7522. Min Act: -0.1700
Data Index: 6215940 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6272. Min Range: -10.6272
Max Act: 9.7522. Min Act: -0.1700
Data Index: 6071463 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6272. Min Range: -10.6272
Max Act: 9.7522. Min Act: -0.1700
Data Index: 3813734 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6272. Min Range: -10.6272
Max Act: 9.7522. Min Act: -0.1700
Data Index: 5556451 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6272. Min Range: -10.6272
Max Act: 9.6897. Min Act: -0.1700
Data Index: 7893773 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6272. Min Range: -10.6272
Max Act: 9.6897. Min Act: -0.1700
Data Index: 5872779 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6272. Min Range: -10.6272
Max Act: 9.6897. Min Act: -0.1700
Data Index: 2209678 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6272. Min Range: -10.6272
Max Act: 9.6897. Min Act: -0.1700
Data Index: 5433529 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6272. Min Range: -10.6272
Max Act: 9.6897. Min Act: -0.1700
Data Index: 4915415 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19