Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1647 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.5131. Min Act: -0.1700
Data Index: 200045 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.3667. Min Act: -0.1700
Data Index: 6375464 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.3339. Min Act: -0.1700
Data Index: 7645843 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.3011. Min Act: -0.1700
Data Index: 5871311 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.3011. Min Act: -0.1700
Data Index: 5890695 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.2846. Min Act: -0.1700
Data Index: 8340267 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.2846. Min Act: -0.1700
Data Index: 1084010 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.2681. Min Act: -0.1700
Data Index: 4206523 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.2516. Min Act: -0.1700
Data Index: 7750755 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.2516. Min Act: -0.1700
Data Index: 2763633 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.2681. Min Act: -0.1700
Data Index: 2852278 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.2846. Min Act: -0.1700
Data Index: 6965953 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.2846. Min Act: -0.1700
Data Index: 1855634 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.2516. Min Act: -0.1700
Data Index: 4726343 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.2351. Min Act: -0.1700
Data Index: 3110401 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.2516. Min Act: -0.1700
Data Index: 4325097 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.2351. Min Act: -0.1700
Data Index: 7942133 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.2516. Min Act: -0.1700
Data Index: 787610 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.2351. Min Act: -0.1700
Data Index: 8007357 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5131. Min Range: -2.5131
Max Act: 2.2351. Min Act: -0.1700
Data Index: 6302732 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19