Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3721 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1878. Min Range: -8.1878
Max Act: 8.1878. Min Act: -0.1700
Data Index: 273250 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1878. Min Range: -8.1878
Max Act: 8.1253. Min Act: -0.1700
Data Index: 7931626 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1878. Min Range: -8.1878
Max Act: 8.0628. Min Act: -0.1700
Data Index: 5516415 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1878. Min Range: -8.1878
Max Act: 8.0003. Min Act: -0.1700
Data Index: 3473924 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1878. Min Range: -8.1878
Max Act: 7.9378. Min Act: -0.1700
Data Index: 407727 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1878. Min Range: -8.1878
Max Act: 7.9378. Min Act: -0.1700
Data Index: 1543237 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1878. Min Range: -8.1878
Max Act: 7.9378. Min Act: -0.1700
Data Index: 4523493 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1878. Min Range: -8.1878
Max Act: 7.8128. Min Act: -0.1700
Data Index: 7293443 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1878. Min Range: -8.1878
Max Act: 7.8128. Min Act: -0.1700
Data Index: 5990464 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1878. Min Range: -8.1878
Max Act: 7.8128. Min Act: -0.1700
Data Index: 7628742 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1878. Min Range: -8.1878
Max Act: 7.8128. Min Act: -0.1700
Data Index: 516489 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1878. Min Range: -8.1878
Max Act: 7.7503. Min Act: -0.1700
Data Index: 443200 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1878. Min Range: -8.1878
Max Act: 7.7503. Min Act: -0.1700
Data Index: 4211274 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1878. Min Range: -8.1878
Max Act: 7.8128. Min Act: -0.1700
Data Index: 3266017 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1878. Min Range: -8.1878
Max Act: 7.7503. Min Act: -0.1700
Data Index: 2508616 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1878. Min Range: -8.1878
Max Act: 7.6878. Min Act: -0.1700
Data Index: 4325413 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1878. Min Range: -8.1878
Max Act: 7.6878. Min Act: -0.1700
Data Index: 2449168 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1878. Min Range: -8.1878
Max Act: 7.6878. Min Act: -0.1700
Data Index: 1321623 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1878. Min Range: -8.1878
Max Act: 7.6878. Min Act: -0.1700
Data Index: 3320426 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1878. Min Range: -8.1878
Max Act: 7.6878. Min Act: -0.1700
Data Index: 6619440 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19