Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4040 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3291. Min Range: -8.3291
Max Act: 8.3291. Min Act: -0.1700
Data Index: 7169909 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3291. Min Range: -8.3291
Max Act: 8.2666. Min Act: -0.1700
Data Index: 7729527 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3291. Min Range: -8.3291
Max Act: 8.2041. Min Act: -0.1700
Data Index: 5291611 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3291. Min Range: -8.3291
Max Act: 8.0791. Min Act: -0.1700
Data Index: 1342454 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3291. Min Range: -8.3291
Max Act: 8.0166. Min Act: -0.1700
Data Index: 6744688 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3291. Min Range: -8.3291
Max Act: 8.0166. Min Act: -0.1700
Data Index: 4135486 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3291. Min Range: -8.3291
Max Act: 8.0166. Min Act: -0.1700
Data Index: 940548 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3291. Min Range: -8.3291
Max Act: 8.0166. Min Act: -0.1700
Data Index: 5856624 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3291. Min Range: -8.3291
Max Act: 7.9541. Min Act: -0.1700
Data Index: 1385716 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3291. Min Range: -8.3291
Max Act: 7.9541. Min Act: -0.1700
Data Index: 7012002 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3291. Min Range: -8.3291
Max Act: 7.8291. Min Act: -0.1700
Data Index: 6429049 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3291. Min Range: -8.3291
Max Act: 7.8916. Min Act: -0.1700
Data Index: 6053647 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3291. Min Range: -8.3291
Max Act: 7.8291. Min Act: -0.1700
Data Index: 7411857 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3291. Min Range: -8.3291
Max Act: 7.8291. Min Act: -0.1700
Data Index: 2139775 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3291. Min Range: -8.3291
Max Act: 7.8291. Min Act: -0.1700
Data Index: 6318837 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3291. Min Range: -8.3291
Max Act: 7.8291. Min Act: -0.1700
Data Index: 2992281 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3291. Min Range: -8.3291
Max Act: 7.8916. Min Act: -0.1700
Data Index: 3649248 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3291. Min Range: -8.3291
Max Act: 7.8291. Min Act: -0.1700
Data Index: 1621985 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3291. Min Range: -8.3291
Max Act: 7.7666. Min Act: -0.1700
Data Index: 7489374 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3291. Min Range: -8.3291
Max Act: 7.7666. Min Act: -0.1700
Data Index: 2782608 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19