Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 796 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4222. Min Range: -8.4222
Max Act: 8.4222. Min Act: -0.1700
Data Index: 5185103 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4222. Min Range: -8.4222
Max Act: 8.3597. Min Act: -0.1700
Data Index: 4516723 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4222. Min Range: -8.4222
Max Act: 8.3284. Min Act: -0.1700
Data Index: 5036641 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4222. Min Range: -8.4222
Max Act: 8.2034. Min Act: -0.1700
Data Index: 5693805 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4222. Min Range: -8.4222
Max Act: 8.0159. Min Act: -0.1700
Data Index: 3101524 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4222. Min Range: -8.4222
Max Act: 8.0159. Min Act: -0.1700
Data Index: 5970617 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4222. Min Range: -8.4222
Max Act: 7.9222. Min Act: -0.1700
Data Index: 2255546 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4222. Min Range: -8.4222
Max Act: 7.8597. Min Act: -0.1700
Data Index: 6811154 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4222. Min Range: -8.4222
Max Act: 7.9222. Min Act: -0.1700
Data Index: 6602051 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4222. Min Range: -8.4222
Max Act: 7.8909. Min Act: -0.1700
Data Index: 7140333 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4222. Min Range: -8.4222
Max Act: 7.8284. Min Act: -0.1700
Data Index: 3645747 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4222. Min Range: -8.4222
Max Act: 7.7972. Min Act: -0.1700
Data Index: 6390796 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4222. Min Range: -8.4222
Max Act: 7.7972. Min Act: -0.1700
Data Index: 2368893 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4222. Min Range: -8.4222
Max Act: 7.7659. Min Act: -0.1700
Data Index: 2236298 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4222. Min Range: -8.4222
Max Act: 7.7347. Min Act: -0.1700
Data Index: 4204981 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4222. Min Range: -8.4222
Max Act: 7.7347. Min Act: -0.1700
Data Index: 4307641 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4222. Min Range: -8.4222
Max Act: 7.6722. Min Act: -0.1700
Data Index: 8531073 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4222. Min Range: -8.4222
Max Act: 7.6409. Min Act: -0.1700
Data Index: 3538164 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4222. Min Range: -8.4222
Max Act: 7.6409. Min Act: -0.1700
Data Index: 6671529 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4222. Min Range: -8.4222
Max Act: 7.6409. Min Act: -0.1700
Data Index: 387284 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19