Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2596 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.7301. Min Act: -0.1700
Data Index: 1383680 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.5426. Min Act: -0.1700
Data Index: 1562153 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.5426. Min Act: -0.1700
Data Index: 8763542 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.5114. Min Act: -0.1700
Data Index: 1617823 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.5114. Min Act: -0.1700
Data Index: 8594844 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.4489. Min Act: -0.1700
Data Index: 7310000 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.4801. Min Act: -0.1700
Data Index: 8194895 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.4801. Min Act: -0.1700
Data Index: 3953720 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.4801. Min Act: -0.1700
Data Index: 8069456 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.3864. Min Act: -0.1700
Data Index: 8280213 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.4176. Min Act: -0.1700
Data Index: 4262661 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.3864. Min Act: -0.1700
Data Index: 4200911 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.3239. Min Act: -0.1700
Data Index: 2161245 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.3864. Min Act: -0.1700
Data Index: 3752198 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.3239. Min Act: -0.1700
Data Index: 3763011 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.3239. Min Act: -0.1700
Data Index: 8594038 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.2926. Min Act: -0.1700
Data Index: 6522698 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.2926. Min Act: -0.1700
Data Index: 4055962 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.2926. Min Act: -0.1700
Data Index: 5259750 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7301. Min Range: -5.7301
Max Act: 5.2926. Min Act: -0.1700
Data Index: 7461325 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19