Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 617 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.7649. Min Range: -9.7649
Max Act: 9.7649. Min Act: -0.1700
Data Index: 707985 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7649. Min Range: -9.7649
Max Act: 9.3899. Min Act: -0.1700
Data Index: 2840305 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7649. Min Range: -9.7649
Max Act: 9.3274. Min Act: -0.1700
Data Index: 6814522 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7649. Min Range: -9.7649
Max Act: 9.0774. Min Act: -0.1700
Data Index: 2830745 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7649. Min Range: -9.7649
Max Act: 9.0774. Min Act: -0.1700
Data Index: 6814531 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7649. Min Range: -9.7649
Max Act: 9.0149. Min Act: -0.1700
Data Index: 6814523 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7649. Min Range: -9.7649
Max Act: 9.0149. Min Act: -0.1700
Data Index: 7445164 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7649. Min Range: -9.7649
Max Act: 9.0149. Min Act: -0.1700
Data Index: 6814533 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7649. Min Range: -9.7649
Max Act: 9.0149. Min Act: -0.1700
Data Index: 6814527 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7649. Min Range: -9.7649
Max Act: 8.9524. Min Act: -0.1700
Data Index: 1271371 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7649. Min Range: -9.7649
Max Act: 8.9524. Min Act: -0.1700
Data Index: 1343772 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7649. Min Range: -9.7649
Max Act: 8.8899. Min Act: -0.1700
Data Index: 1199137 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7649. Min Range: -9.7649
Max Act: 8.8274. Min Act: -0.1700
Data Index: 6814530 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7649. Min Range: -9.7649
Max Act: 8.7024. Min Act: -0.1700
Data Index: 6808064 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7649. Min Range: -9.7649
Max Act: 8.7649. Min Act: -0.1700
Data Index: 2175630 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7649. Min Range: -9.7649
Max Act: 8.7024. Min Act: -0.1700
Data Index: 4460153 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7649. Min Range: -9.7649
Max Act: 8.6399. Min Act: -0.1700
Data Index: 1119242 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7649. Min Range: -9.7649
Max Act: 8.7649. Min Act: -0.1700
Data Index: 3842495 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7649. Min Range: -9.7649
Max Act: 8.7024. Min Act: -0.1700
Data Index: 1989439 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7649. Min Range: -9.7649
Max Act: 8.6399. Min Act: -0.1700
Data Index: 13395 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19