Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 974 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.8272. Min Act: -0.1700
Data Index: 5171787 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.7803. Min Act: -0.1700
Data Index: 6953019 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.7490. Min Act: -0.1700
Data Index: 3153757 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.7490. Min Act: -0.1700
Data Index: 6229521 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.7803. Min Act: -0.1700
Data Index: 2213624 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.7333. Min Act: -0.1700
Data Index: 3770667 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.7177. Min Act: -0.1700
Data Index: 5308244 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.7021. Min Act: -0.1700
Data Index: 814362 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.6864. Min Act: -0.1700
Data Index: 4246317 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.6708. Min Act: -0.1700
Data Index: 814359 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.6551. Min Act: -0.1700
Data Index: 814358 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.6238. Min Act: -0.1700
Data Index: 5111459 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.6395. Min Act: -0.1700
Data Index: 8797010 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.6238. Min Act: -0.1700
Data Index: 7294454 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.6238. Min Act: -0.1700
Data Index: 7399045 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.5925. Min Act: -0.1700
Data Index: 4985014 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.6238. Min Act: -0.1700
Data Index: 5626125 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.6395. Min Act: -0.1700
Data Index: 5367552 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.5925. Min Act: -0.1700
Data Index: 8491984 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8272. Min Range: -3.8272
Max Act: 3.6082. Min Act: -0.1700
Data Index: 814368 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19