Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3642 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3748. Min Range: -8.3748
Max Act: 8.3748. Min Act: -0.1700
Data Index: 7979439 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3748. Min Range: -8.3748
Max Act: 7.6248. Min Act: -0.1700
Data Index: 7240781 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3748. Min Range: -8.3748
Max Act: 7.5935. Min Act: -0.1700
Data Index: 7979441 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3748. Min Range: -8.3748
Max Act: 7.4373. Min Act: -0.1700
Data Index: 1023631 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3748. Min Range: -8.3748
Max Act: 7.3123. Min Act: -0.1700
Data Index: 4744423 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3748. Min Range: -8.3748
Max Act: 7.3123. Min Act: -0.1700
Data Index: 2037956 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3748. Min Range: -8.3748
Max Act: 7.3123. Min Act: -0.1700
Data Index: 3148968 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3748. Min Range: -8.3748
Max Act: 7.3123. Min Act: -0.1700
Data Index: 1886048 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3748. Min Range: -8.3748
Max Act: 7.2810. Min Act: -0.1700
Data Index: 6119594 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3748. Min Range: -8.3748
Max Act: 7.2810. Min Act: -0.1700
Data Index: 6609315 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3748. Min Range: -8.3748
Max Act: 7.3123. Min Act: -0.1700
Data Index: 1731310 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3748. Min Range: -8.3748
Max Act: 7.3435. Min Act: -0.1700
Data Index: 3767722 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3748. Min Range: -8.3748
Max Act: 7.3435. Min Act: -0.1700
Data Index: 3160067 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3748. Min Range: -8.3748
Max Act: 7.2185. Min Act: -0.1700
Data Index: 8557389 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3748. Min Range: -8.3748
Max Act: 7.1873. Min Act: -0.1700
Data Index: 3519067 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3748. Min Range: -8.3748
Max Act: 7.2498. Min Act: -0.1700
Data Index: 8474364 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3748. Min Range: -8.3748
Max Act: 7.3123. Min Act: -0.1700
Data Index: 6660873 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3748. Min Range: -8.3748
Max Act: 7.2185. Min Act: -0.1700
Data Index: 5783178 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3748. Min Range: -8.3748
Max Act: 7.2498. Min Act: -0.1700
Data Index: 1263188 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3748. Min Range: -8.3748
Max Act: 7.2185. Min Act: -0.1700
Data Index: 3375171 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19