Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3875 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.7753. Min Act: -0.1700
Data Index: 5760080 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.7753. Min Act: -0.1700
Data Index: 5823684 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.7753. Min Act: -0.1700
Data Index: 6410788 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.7440. Min Act: -0.1700
Data Index: 1483309 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.6502. Min Act: -0.1700
Data Index: 6533204 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.6502. Min Act: -0.1700
Data Index: 5674722 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.6189. Min Act: -0.1700
Data Index: 3001869 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.5876. Min Act: -0.1700
Data Index: 3856379 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.5876. Min Act: -0.1700
Data Index: 6429283 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.5563. Min Act: -0.1700
Data Index: 7260606 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.5719. Min Act: -0.1700
Data Index: 2838546 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.5563. Min Act: -0.1700
Data Index: 1655435 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.5563. Min Act: -0.1700
Data Index: 5528206 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.5249. Min Act: -0.1700
Data Index: 1249862 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.4936. Min Act: -0.1700
Data Index: 3129087 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.4780. Min Act: -0.1700
Data Index: 8195559 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.4623. Min Act: -0.1700
Data Index: 2697809 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.4466. Min Act: -0.1700
Data Index: 6476561 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.4310. Min Act: -0.1700
Data Index: 7627457 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7753. Min Range: -3.7753
Max Act: 3.4153. Min Act: -0.1700
Data Index: 3001870 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19