Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 12.9222. Min Range: -12.9222
Max Act: 12.9222. Min Act: -0.1700
Data Index: 1711445 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.9222. Min Range: -12.9222
Max Act: 12.9222. Min Act: -0.1700
Data Index: 3702048 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.9222. Min Range: -12.9222
Max Act: 12.9222. Min Act: -0.1700
Data Index: 4810820 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.9222. Min Range: -12.9222
Max Act: 12.2972. Min Act: -0.1700
Data Index: 7741960 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.9222. Min Range: -12.9222
Max Act: 12.3597. Min Act: -0.1700
Data Index: 8186802 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.9222. Min Range: -12.9222
Max Act: 11.9847. Min Act: -0.1700
Data Index: 7301947 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.9222. Min Range: -12.9222
Max Act: 11.4222. Min Act: -0.1700
Data Index: 1729959 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.9222. Min Range: -12.9222
Max Act: 11.0472. Min Act: -0.1700
Data Index: 4033398 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.9222. Min Range: -12.9222
Max Act: 10.9847. Min Act: -0.1700
Data Index: 5665003 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.9222. Min Range: -12.9222
Max Act: 10.7972. Min Act: -0.1700
Data Index: 7338589 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.9222. Min Range: -12.9222
Max Act: 11.3597. Min Act: -0.1700
Data Index: 4500087 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.9222. Min Range: -12.9222
Max Act: 11.1097. Min Act: -0.1700
Data Index: 3494304 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.9222. Min Range: -12.9222
Max Act: 10.7972. Min Act: -0.1700
Data Index: 1729960 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.9222. Min Range: -12.9222
Max Act: 10.7347. Min Act: -0.1700
Data Index: 2977622 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.9222. Min Range: -12.9222
Max Act: 10.4847. Min Act: -0.1700
Data Index: 2051466 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.9222. Min Range: -12.9222
Max Act: 10.4222. Min Act: -0.1700
Data Index: 714432 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.9222. Min Range: -12.9222
Max Act: 10.4847. Min Act: -0.1700
Data Index: 1794348 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.9222. Min Range: -12.9222
Max Act: 10.2347. Min Act: -0.1700
Data Index: 949577 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.9222. Min Range: -12.9222
Max Act: 10.2972. Min Act: -0.1700
Data Index: 386967 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.9222. Min Range: -12.9222
Max Act: 10.0472. Min Act: -0.1700
Data Index: 1481139 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19