Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3145 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5434. Min Range: -6.5434
Max Act: 6.5434. Min Act: -0.1700
Data Index: 5313415 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5434. Min Range: -6.5434
Max Act: 6.1059. Min Act: -0.1700
Data Index: 6278498 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5434. Min Range: -6.5434
Max Act: 6.0746. Min Act: -0.1700
Data Index: 399041 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5434. Min Range: -6.5434
Max Act: 5.9496. Min Act: -0.1700
Data Index: 6297133 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5434. Min Range: -6.5434
Max Act: 5.9496. Min Act: -0.1700
Data Index: 2664305 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5434. Min Range: -6.5434
Max Act: 5.9184. Min Act: -0.1700
Data Index: 195733 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5434. Min Range: -6.5434
Max Act: 5.7934. Min Act: -0.1700
Data Index: 3196574 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5434. Min Range: -6.5434
Max Act: 5.7934. Min Act: -0.1700
Data Index: 4292623 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5434. Min Range: -6.5434
Max Act: 5.7309. Min Act: -0.1700
Data Index: 385526 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5434. Min Range: -6.5434
Max Act: 5.7309. Min Act: -0.1700
Data Index: 3276352 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5434. Min Range: -6.5434
Max Act: 5.7309. Min Act: -0.1700
Data Index: 374981 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5434. Min Range: -6.5434
Max Act: 5.6996. Min Act: -0.1700
Data Index: 4204616 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5434. Min Range: -6.5434
Max Act: 5.6996. Min Act: -0.1700
Data Index: 1340822 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5434. Min Range: -6.5434
Max Act: 5.6684. Min Act: -0.1700
Data Index: 4307982 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5434. Min Range: -6.5434
Max Act: 5.6684. Min Act: -0.1700
Data Index: 2475915 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5434. Min Range: -6.5434
Max Act: 5.6371. Min Act: -0.1700
Data Index: 2347427 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5434. Min Range: -6.5434
Max Act: 5.6684. Min Act: -0.1700
Data Index: 7864706 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5434. Min Range: -6.5434
Max Act: 5.6059. Min Act: -0.1700
Data Index: 4425121 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5434. Min Range: -6.5434
Max Act: 5.6059. Min Act: -0.1700
Data Index: 8390647 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5434. Min Range: -6.5434
Max Act: 5.6059. Min Act: -0.1700
Data Index: 5750679 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19