Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2566 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.5707. Min Act: -0.1700
Data Index: 4208586 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.4770. Min Act: -0.1700
Data Index: 7377426 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.4457. Min Act: -0.1700
Data Index: 4468283 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.4457. Min Act: -0.1700
Data Index: 3398004 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.4145. Min Act: -0.1700
Data Index: 3734894 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.3832. Min Act: -0.1700
Data Index: 2193781 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.3207. Min Act: -0.1700
Data Index: 7295045 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.2895. Min Act: -0.1700
Data Index: 3003681 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.3207. Min Act: -0.1700
Data Index: 445999 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.2895. Min Act: -0.1700
Data Index: 5164163 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.2270. Min Act: -0.1700
Data Index: 4461278 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.2582. Min Act: -0.1700
Data Index: 7807517 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.2582. Min Act: -0.1700
Data Index: 4531279 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.2582. Min Act: -0.1700
Data Index: 7919306 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.2270. Min Act: -0.1700
Data Index: 6265690 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.2270. Min Act: -0.1700
Data Index: 2679772 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.2270. Min Act: -0.1700
Data Index: 176756 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.2270. Min Act: -0.1700
Data Index: 6003891 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.1645. Min Act: -0.1700
Data Index: 4587776 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5707. Min Range: -5.5707
Max Act: 5.1645. Min Act: -0.1700
Data Index: 6924508 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19