Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2232. Min Range: -7.2232
Max Act: 7.2232. Min Act: -0.1700
Data Index: 2076463 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2232. Min Range: -7.2232
Max Act: 7.0357. Min Act: -0.1700
Data Index: 1939012 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2232. Min Range: -7.2232
Max Act: 6.9419. Min Act: -0.1700
Data Index: 6627788 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2232. Min Range: -7.2232
Max Act: 6.9419. Min Act: -0.1700
Data Index: 8567520 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2232. Min Range: -7.2232
Max Act: 6.8482. Min Act: -0.1700
Data Index: 7329396 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2232. Min Range: -7.2232
Max Act: 6.8169. Min Act: -0.1700
Data Index: 3312172 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2232. Min Range: -7.2232
Max Act: 6.8169. Min Act: -0.1700
Data Index: 2437920 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2232. Min Range: -7.2232
Max Act: 6.7544. Min Act: -0.1700
Data Index: 8124862 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2232. Min Range: -7.2232
Max Act: 6.6919. Min Act: -0.1700
Data Index: 1039715 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2232. Min Range: -7.2232
Max Act: 6.6607. Min Act: -0.1700
Data Index: 1167975 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2232. Min Range: -7.2232
Max Act: 6.6294. Min Act: -0.1700
Data Index: 6440706 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2232. Min Range: -7.2232
Max Act: 6.6294. Min Act: -0.1700
Data Index: 3756442 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2232. Min Range: -7.2232
Max Act: 6.5982. Min Act: -0.1700
Data Index: 6508683 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2232. Min Range: -7.2232
Max Act: 6.6294. Min Act: -0.1700
Data Index: 2240388 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2232. Min Range: -7.2232
Max Act: 6.5982. Min Act: -0.1700
Data Index: 4303071 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2232. Min Range: -7.2232
Max Act: 6.5982. Min Act: -0.1700
Data Index: 2463639 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2232. Min Range: -7.2232
Max Act: 6.5982. Min Act: -0.1700
Data Index: 4230940 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2232. Min Range: -7.2232
Max Act: 6.5982. Min Act: -0.1700
Data Index: 3704369 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2232. Min Range: -7.2232
Max Act: 6.5982. Min Act: -0.1700
Data Index: 6044810 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2232. Min Range: -7.2232
Max Act: 6.5669. Min Act: -0.1700
Data Index: 6269921 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19