Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2825 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.2977. Min Act: -0.1700
Data Index: 4356739 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.2977. Min Act: -0.1700
Data Index: 3106694 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.2977. Min Act: -0.1700
Data Index: 1525635 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.2505. Min Act: -0.1700
Data Index: 7829001 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.2820. Min Act: -0.1700
Data Index: 2039331 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.2191. Min Act: -0.1700
Data Index: 8454253 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.2505. Min Act: -0.1700
Data Index: 7920454 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.2348. Min Act: -0.1700
Data Index: 3011555 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.2191. Min Act: -0.1700
Data Index: 6345296 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.2191. Min Act: -0.1700
Data Index: 3011554 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.2034. Min Act: -0.1700
Data Index: 8722738 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.2034. Min Act: -0.1700
Data Index: 2495967 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.2034. Min Act: -0.1700
Data Index: 1685748 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.2034. Min Act: -0.1700
Data Index: 7148887 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.2034. Min Act: -0.1700
Data Index: 867451 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.2034. Min Act: -0.1700
Data Index: 8810507 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.2034. Min Act: -0.1700
Data Index: 817323 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.1562. Min Act: -0.1700
Data Index: 2526258 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.1719. Min Act: -0.1700
Data Index: 1622353 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2977. Min Range: -3.2977
Max Act: 3.2034. Min Act: -0.1700
Data Index: 7668307 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19