Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1335 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0198. Min Range: -4.0198
Max Act: 4.0198. Min Act: -0.1700
Data Index: 2084034 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0198. Min Range: -4.0198
Max Act: 3.9729. Min Act: -0.1700
Data Index: 2339314 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0198. Min Range: -4.0198
Max Act: 3.9573. Min Act: -0.1700
Data Index: 5158672 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0198. Min Range: -4.0198
Max Act: 3.9729. Min Act: -0.1700
Data Index: 893928 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0198. Min Range: -4.0198
Max Act: 3.9260. Min Act: -0.1700
Data Index: 6310235 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0198. Min Range: -4.0198
Max Act: 3.8947. Min Act: -0.1700
Data Index: 1556816 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0198. Min Range: -4.0198
Max Act: 3.8947. Min Act: -0.1700
Data Index: 968651 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0198. Min Range: -4.0198
Max Act: 3.8791. Min Act: -0.1700
Data Index: 2392607 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0198. Min Range: -4.0198
Max Act: 3.9104. Min Act: -0.1700
Data Index: 6897229 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0198. Min Range: -4.0198
Max Act: 3.8791. Min Act: -0.1700
Data Index: 2488846 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0198. Min Range: -4.0198
Max Act: 3.8947. Min Act: -0.1700
Data Index: 2355889 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0198. Min Range: -4.0198
Max Act: 3.9104. Min Act: -0.1700
Data Index: 6073899 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0198. Min Range: -4.0198
Max Act: 3.8947. Min Act: -0.1700
Data Index: 3586181 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0198. Min Range: -4.0198
Max Act: 3.8635. Min Act: -0.1700
Data Index: 8625284 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0198. Min Range: -4.0198
Max Act: 3.8635. Min Act: -0.1700
Data Index: 5196555 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0198. Min Range: -4.0198
Max Act: 3.8166. Min Act: -0.1700
Data Index: 3826237 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0198. Min Range: -4.0198
Max Act: 3.8478. Min Act: -0.1700
Data Index: 8730993 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0198. Min Range: -4.0198
Max Act: 3.8791. Min Act: -0.1700
Data Index: 8628587 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0198. Min Range: -4.0198
Max Act: 3.8322. Min Act: -0.1700
Data Index: 446143 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0198. Min Range: -4.0198
Max Act: 3.8322. Min Act: -0.1700
Data Index: 779929 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19