Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2414. Min Range: -6.2414
Max Act: 6.2414. Min Act: -0.1700
Data Index: 3901357 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2414. Min Range: -6.2414
Max Act: 5.8664. Min Act: -0.1700
Data Index: 5440931 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2414. Min Range: -6.2414
Max Act: 5.7414. Min Act: -0.1700
Data Index: 2885842 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2414. Min Range: -6.2414
Max Act: 5.6789. Min Act: -0.1700
Data Index: 2984376 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2414. Min Range: -6.2414
Max Act: 5.6476. Min Act: -0.1700
Data Index: 2780040 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2414. Min Range: -6.2414
Max Act: 5.6476. Min Act: -0.1700
Data Index: 4501816 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2414. Min Range: -6.2414
Max Act: 5.6789. Min Act: -0.1700
Data Index: 3745977 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2414. Min Range: -6.2414
Max Act: 5.6164. Min Act: -0.1700
Data Index: 118232 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2414. Min Range: -6.2414
Max Act: 5.6164. Min Act: -0.1700
Data Index: 6434618 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2414. Min Range: -6.2414
Max Act: 5.6476. Min Act: -0.1700
Data Index: 3870283 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2414. Min Range: -6.2414
Max Act: 5.5851. Min Act: -0.1700
Data Index: 3185110 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2414. Min Range: -6.2414
Max Act: 5.5851. Min Act: -0.1700
Data Index: 3310817 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2414. Min Range: -6.2414
Max Act: 5.5539. Min Act: -0.1700
Data Index: 2718386 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2414. Min Range: -6.2414
Max Act: 5.5539. Min Act: -0.1700
Data Index: 3111995 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2414. Min Range: -6.2414
Max Act: 5.5226. Min Act: -0.1700
Data Index: 5094081 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2414. Min Range: -6.2414
Max Act: 5.4914. Min Act: -0.1700
Data Index: 2093030 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2414. Min Range: -6.2414
Max Act: 5.5226. Min Act: -0.1700
Data Index: 6078701 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2414. Min Range: -6.2414
Max Act: 5.5226. Min Act: -0.1700
Data Index: 410621 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2414. Min Range: -6.2414
Max Act: 5.4914. Min Act: -0.1700
Data Index: 3965723 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2414. Min Range: -6.2414
Max Act: 5.5539. Min Act: -0.1700
Data Index: 3506161 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19