Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.3414. Min Range: -5.3414
Max Act: 5.3398. Min Act: -0.1700
Data Index: 5189752 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 5.3414. Min Range: -5.3414
Max Act: 5.3414. Min Act: -0.1700
Data Index: 6312542 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 5.3414. Min Range: -5.3414
Max Act: 5.3197. Min Act: -0.1700
Data Index: 8631525 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 5.3414. Min Range: -5.3414
Max Act: 5.1463. Min Act: -0.1700
Data Index: 3853902 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 5.3414. Min Range: -5.3414
Max Act: 5.1031. Min Act: -0.1700
Data Index: 6515149 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 5.3414. Min Range: -5.3414
Max Act: 5.0877. Min Act: -0.1700
Data Index: 3191691 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 5.3414. Min Range: -5.3414
Max Act: 5.0531. Min Act: -0.1700
Data Index: 8445930 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 5.3414. Min Range: -5.3414
Max Act: 5.0332. Min Act: -0.1700
Data Index: 513642 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 5.3414. Min Range: -5.3414
Max Act: 5.0137. Min Act: -0.1700
Data Index: 5578051 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 5.3414. Min Range: -5.3414
Max Act: 4.9800. Min Act: -0.1700
Data Index: 6878082 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 5.3414. Min Range: -5.3414
Max Act: 5.0235. Min Act: -0.1700
Data Index: 8825115 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 5.3414. Min Range: -5.3414
Max Act: 5.0138. Min Act: -0.1700
Data Index: 5796532 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 5.3414. Min Range: -5.3414
Max Act: 4.9690. Min Act: -0.1700
Data Index: 2522436 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 5.3414. Min Range: -5.3414
Max Act: 4.9804. Min Act: -0.1700
Data Index: 3898732 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 5.3414. Min Range: -5.3414
Max Act: 4.9941. Min Act: -0.1700
Data Index: 1730561 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 5.3414. Min Range: -5.3414
Max Act: 4.9938. Min Act: -0.1700
Data Index: 7649741 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 5.3414. Min Range: -5.3414
Max Act: 4.9634. Min Act: -0.1700
Data Index: 5332971 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 5.3414. Min Range: -5.3414
Max Act: 4.9222. Min Act: -0.1700
Data Index: 1846163 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 5.3414. Min Range: -5.3414
Max Act: 4.9347. Min Act: -0.1700
Data Index: 2269022 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 5.3414. Min Range: -5.3414
Max Act: 4.9505. Min Act: -0.1700
Data Index: 5189755 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full textTruncated
Full Text #19