Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3486 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.7662. Min Act: -0.1700
Data Index: 4112860 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.7350. Min Act: -0.1700
Data Index: 5615493 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.7037. Min Act: -0.1700
Data Index: 2897495 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.6725. Min Act: -0.1700
Data Index: 5024862 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.6412. Min Act: -0.1700
Data Index: 805653 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5787. Min Act: -0.1700
Data Index: 321079 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5787. Min Act: -0.1700
Data Index: 3574707 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5475. Min Act: -0.1700
Data Index: 3588801 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.6100. Min Act: -0.1700
Data Index: 5743631 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5475. Min Act: -0.1700
Data Index: 3666340 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5475. Min Act: -0.1700
Data Index: 1687607 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5475. Min Act: -0.1700
Data Index: 7422227 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5475. Min Act: -0.1700
Data Index: 6772437 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5162. Min Act: -0.1700
Data Index: 352818 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5162. Min Act: -0.1700
Data Index: 3234471 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5475. Min Act: -0.1700
Data Index: 1492458 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5162. Min Act: -0.1700
Data Index: 7199712 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4850. Min Act: -0.1700
Data Index: 4415649 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4850. Min Act: -0.1700
Data Index: 3258882 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4850. Min Act: -0.1700
Data Index: 2827294 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19