Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4070 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.4514. Min Act: -0.1700
Data Index: 2361803 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.3264. Min Act: -0.1700
Data Index: 8279448 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.3264. Min Act: -0.1700
Data Index: 1994076 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.2951. Min Act: -0.1700
Data Index: 8592019 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.2951. Min Act: -0.1700
Data Index: 7453766 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.2326. Min Act: -0.1700
Data Index: 2009708 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.2639. Min Act: -0.1700
Data Index: 8116793 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.2639. Min Act: -0.1700
Data Index: 5372915 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.2639. Min Act: -0.1700
Data Index: 2819744 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.2326. Min Act: -0.1700
Data Index: 2819732 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.2639. Min Act: -0.1700
Data Index: 6574527 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.2014. Min Act: -0.1700
Data Index: 2819747 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.2014. Min Act: -0.1700
Data Index: 2807995 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.2014. Min Act: -0.1700
Data Index: 3331236 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.2014. Min Act: -0.1700
Data Index: 2819721 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.2014. Min Act: -0.1700
Data Index: 4535051 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.1701. Min Act: -0.1700
Data Index: 2819748 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.1701. Min Act: -0.1700
Data Index: 4347434 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.1701. Min Act: -0.1700
Data Index: 673082 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4514. Min Range: -4.4514
Max Act: 4.1388. Min Act: -0.1700
Data Index: 542900 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19