Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2076 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.6315. Min Act: -0.1700
Data Index: 6506075 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.6003. Min Act: -0.1700
Data Index: 3122345 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.5378. Min Act: -0.1700
Data Index: 5582678 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.4753. Min Act: -0.1700
Data Index: 4761003 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.4753. Min Act: -0.1700
Data Index: 7172738 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.4440. Min Act: -0.1700
Data Index: 3533587 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.4440. Min Act: -0.1700
Data Index: 5920568 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.3815. Min Act: -0.1700
Data Index: 3638491 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.4440. Min Act: -0.1700
Data Index: 157868 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.4128. Min Act: -0.1700
Data Index: 5683409 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.3815. Min Act: -0.1700
Data Index: 5369048 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.4128. Min Act: -0.1700
Data Index: 5932361 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.3815. Min Act: -0.1700
Data Index: 3057431 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.3815. Min Act: -0.1700
Data Index: 7346077 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.3190. Min Act: -0.1700
Data Index: 2769277 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.3815. Min Act: -0.1700
Data Index: 6045028 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.3503. Min Act: -0.1700
Data Index: 2396345 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.2878. Min Act: -0.1700
Data Index: 20772 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.2565. Min Act: -0.1700
Data Index: 4806219 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6315. Min Range: -6.6315
Max Act: 6.2253. Min Act: -0.1700
Data Index: 5145322 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19