Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2683 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4514. Min Range: -7.4514
Max Act: 7.4514. Min Act: -0.1700
Data Index: 3444227 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4514. Min Range: -7.4514
Max Act: 7.2952. Min Act: -0.1700
Data Index: 657593 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4514. Min Range: -7.4514
Max Act: 7.1389. Min Act: -0.1700
Data Index: 7825665 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4514. Min Range: -7.4514
Max Act: 7.0452. Min Act: -0.1700
Data Index: 6150122 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4514. Min Range: -7.4514
Max Act: 6.9827. Min Act: -0.1700
Data Index: 2040650 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4514. Min Range: -7.4514
Max Act: 7.0139. Min Act: -0.1700
Data Index: 4608966 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4514. Min Range: -7.4514
Max Act: 6.9514. Min Act: -0.1700
Data Index: 3982911 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4514. Min Range: -7.4514
Max Act: 6.9514. Min Act: -0.1700
Data Index: 8313824 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4514. Min Range: -7.4514
Max Act: 6.9202. Min Act: -0.1700
Data Index: 804576 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4514. Min Range: -7.4514
Max Act: 6.9202. Min Act: -0.1700
Data Index: 699997 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4514. Min Range: -7.4514
Max Act: 6.8889. Min Act: -0.1700
Data Index: 6464981 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4514. Min Range: -7.4514
Max Act: 6.8264. Min Act: -0.1700
Data Index: 6165312 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4514. Min Range: -7.4514
Max Act: 6.8264. Min Act: -0.1700
Data Index: 4865641 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4514. Min Range: -7.4514
Max Act: 6.7639. Min Act: -0.1700
Data Index: 4919349 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4514. Min Range: -7.4514
Max Act: 6.7639. Min Act: -0.1700
Data Index: 2987719 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4514. Min Range: -7.4514
Max Act: 6.7327. Min Act: -0.1700
Data Index: 6152157 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4514. Min Range: -7.4514
Max Act: 6.7639. Min Act: -0.1700
Data Index: 7528544 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4514. Min Range: -7.4514
Max Act: 6.7639. Min Act: -0.1700
Data Index: 455997 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4514. Min Range: -7.4514
Max Act: 6.7327. Min Act: -0.1700
Data Index: 6660940 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4514. Min Range: -7.4514
Max Act: 6.7639. Min Act: -0.1700
Data Index: 3858479 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19