Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3972 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.4664. Min Act: -0.1700
Data Index: 2002859 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.4352. Min Act: -0.1700
Data Index: 7685008 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.3414. Min Act: -0.1700
Data Index: 4114583 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.3414. Min Act: -0.1700
Data Index: 8699998 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.3727. Min Act: -0.1700
Data Index: 2002852 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.3414. Min Act: -0.1700
Data Index: 6255247 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.3102. Min Act: -0.1700
Data Index: 2002862 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.3102. Min Act: -0.1700
Data Index: 4114582 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.3102. Min Act: -0.1700
Data Index: 4508211 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.3102. Min Act: -0.1700
Data Index: 4742727 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.2477. Min Act: -0.1700
Data Index: 317755 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.2789. Min Act: -0.1700
Data Index: 6372020 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.2789. Min Act: -0.1700
Data Index: 6325694 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.2477. Min Act: -0.1700
Data Index: 5349047 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.2789. Min Act: -0.1700
Data Index: 8777438 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.2789. Min Act: -0.1700
Data Index: 8223540 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.2789. Min Act: -0.1700
Data Index: 2650760 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.2477. Min Act: -0.1700
Data Index: 2951413 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.2164. Min Act: -0.1700
Data Index: 6592319 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4664. Min Range: -4.4664
Max Act: 4.2477. Min Act: -0.1700
Data Index: 7175306 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19