Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4844 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2231. Min Range: -6.2231
Max Act: 6.2231. Min Act: -0.1700
Data Index: 2069535 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2231. Min Range: -6.2231
Max Act: 6.0356. Min Act: -0.1700
Data Index: 3326065 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2231. Min Range: -6.2231
Max Act: 6.0044. Min Act: -0.1700
Data Index: 3233989 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2231. Min Range: -6.2231
Max Act: 5.9731. Min Act: -0.1700
Data Index: 426666 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2231. Min Range: -6.2231
Max Act: 5.9419. Min Act: -0.1700
Data Index: 1870049 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2231. Min Range: -6.2231
Max Act: 5.9106. Min Act: -0.1700
Data Index: 3111156 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2231. Min Range: -6.2231
Max Act: 5.9106. Min Act: -0.1700
Data Index: 7391576 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2231. Min Range: -6.2231
Max Act: 5.8794. Min Act: -0.1700
Data Index: 427466 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2231. Min Range: -6.2231
Max Act: 5.8481. Min Act: -0.1700
Data Index: 3579735 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2231. Min Range: -6.2231
Max Act: 5.7856. Min Act: -0.1700
Data Index: 1969543 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2231. Min Range: -6.2231
Max Act: 5.7544. Min Act: -0.1700
Data Index: 7272870 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2231. Min Range: -6.2231
Max Act: 5.7544. Min Act: -0.1700
Data Index: 4924164 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2231. Min Range: -6.2231
Max Act: 5.7231. Min Act: -0.1700
Data Index: 5729009 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2231. Min Range: -6.2231
Max Act: 5.7231. Min Act: -0.1700
Data Index: 7819745 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2231. Min Range: -6.2231
Max Act: 5.7231. Min Act: -0.1700
Data Index: 5703845 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2231. Min Range: -6.2231
Max Act: 5.7231. Min Act: -0.1700
Data Index: 6346968 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2231. Min Range: -6.2231
Max Act: 5.6919. Min Act: -0.1700
Data Index: 781164 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2231. Min Range: -6.2231
Max Act: 5.6606. Min Act: -0.1700
Data Index: 1470918 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2231. Min Range: -6.2231
Max Act: 5.6919. Min Act: -0.1700
Data Index: 1288605 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2231. Min Range: -6.2231
Max Act: 5.6606. Min Act: -0.1700
Data Index: 426665 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19