Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4436 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.5668. Min Act: -0.1700
Data Index: 8077840 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.4731. Min Act: -0.1700
Data Index: 5461273 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.4418. Min Act: -0.1700
Data Index: 4672631 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.4418. Min Act: -0.1700
Data Index: 4105635 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.3793. Min Act: -0.1700
Data Index: 1674183 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.3168. Min Act: -0.1700
Data Index: 1877885 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.3168. Min Act: -0.1700
Data Index: 7274986 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.2231. Min Act: -0.1700
Data Index: 3791895 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.2231. Min Act: -0.1700
Data Index: 6734938 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.1918. Min Act: -0.1700
Data Index: 1445470 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.1918. Min Act: -0.1700
Data Index: 6237228 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.1606. Min Act: -0.1700
Data Index: 551804 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.1918. Min Act: -0.1700
Data Index: 6529575 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.1606. Min Act: -0.1700
Data Index: 5392775 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.1606. Min Act: -0.1700
Data Index: 8385533 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.1293. Min Act: -0.1700
Data Index: 3528355 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.0981. Min Act: -0.1700
Data Index: 3817884 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.0981. Min Act: -0.1700
Data Index: 694589 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.0981. Min Act: -0.1700
Data Index: 4999420 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5668. Min Range: -6.5668
Max Act: 6.0981. Min Act: -0.1700
Data Index: 3890879 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19