Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1177 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8467. Min Range: -8.8467
Max Act: 8.8467. Min Act: -0.1700
Data Index: 1305052 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8467. Min Range: -8.8467
Max Act: 8.0342. Min Act: -0.1700
Data Index: 1488974 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8467. Min Range: -8.8467
Max Act: 7.6592. Min Act: -0.1700
Data Index: 7866703 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8467. Min Range: -8.8467
Max Act: 7.6279. Min Act: -0.1700
Data Index: 8689679 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8467. Min Range: -8.8467
Max Act: 7.5342. Min Act: -0.1700
Data Index: 6175922 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8467. Min Range: -8.8467
Max Act: 7.5967. Min Act: -0.1700
Data Index: 439007 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8467. Min Range: -8.8467
Max Act: 7.4092. Min Act: -0.1700
Data Index: 5019151 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8467. Min Range: -8.8467
Max Act: 7.3467. Min Act: -0.1700
Data Index: 1543472 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8467. Min Range: -8.8467
Max Act: 7.2529. Min Act: -0.1700
Data Index: 2413918 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8467. Min Range: -8.8467
Max Act: 7.2529. Min Act: -0.1700
Data Index: 6029229 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8467. Min Range: -8.8467
Max Act: 7.1904. Min Act: -0.1700
Data Index: 5435038 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8467. Min Range: -8.8467
Max Act: 7.1592. Min Act: -0.1700
Data Index: 3793965 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8467. Min Range: -8.8467
Max Act: 7.1592. Min Act: -0.1700
Data Index: 8183492 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8467. Min Range: -8.8467
Max Act: 7.1279. Min Act: -0.1700
Data Index: 5693296 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8467. Min Range: -8.8467
Max Act: 7.1279. Min Act: -0.1700
Data Index: 7541444 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8467. Min Range: -8.8467
Max Act: 7.1279. Min Act: -0.1700
Data Index: 2100740 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8467. Min Range: -8.8467
Max Act: 7.1279. Min Act: -0.1700
Data Index: 3326300 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8467. Min Range: -8.8467
Max Act: 7.0967. Min Act: -0.1700
Data Index: 1663887 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8467. Min Range: -8.8467
Max Act: 7.0967. Min Act: -0.1700
Data Index: 526483 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8467. Min Range: -8.8467
Max Act: 7.0967. Min Act: -0.1700
Data Index: 2246322 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19