Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3087 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3135. Min Range: -7.3135
Max Act: 7.3135. Min Act: -0.1700
Data Index: 7816281 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3135. Min Range: -7.3135
Max Act: 7.1573. Min Act: -0.1700
Data Index: 3185701 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.9385. Min Act: -0.1700
Data Index: 3687925 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.9073. Min Act: -0.1700
Data Index: 2753919 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.8135. Min Act: -0.1700
Data Index: 7470487 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.8760. Min Act: -0.1700
Data Index: 3666163 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.7823. Min Act: -0.1700
Data Index: 8214924 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.7198. Min Act: -0.1700
Data Index: 317712 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.7198. Min Act: -0.1700
Data Index: 1064408 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.7198. Min Act: -0.1700
Data Index: 8062322 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.6885. Min Act: -0.1700
Data Index: 3303374 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.6885. Min Act: -0.1700
Data Index: 5388298 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.6573. Min Act: -0.1700
Data Index: 4315524 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.6573. Min Act: -0.1700
Data Index: 5219340 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.6573. Min Act: -0.1700
Data Index: 6988865 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.6573. Min Act: -0.1700
Data Index: 3420949 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.6260. Min Act: -0.1700
Data Index: 7939987 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.5948. Min Act: -0.1700
Data Index: 4966661 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.5948. Min Act: -0.1700
Data Index: 1884617 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.5635. Min Act: -0.1700
Data Index: 3108590 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19