Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 171 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.6638. Min Act: -0.1700
Data Index: 1689111 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.6317. Min Act: -0.1700
Data Index: 1704808 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.6317. Min Act: -0.1700
Data Index: 2938813 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.5995. Min Act: -0.1700
Data Index: 7662190 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.5834. Min Act: -0.1700
Data Index: 1752530 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.5834. Min Act: -0.1700
Data Index: 2368082 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.5511. Min Act: -0.1700
Data Index: 6426771 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.5511. Min Act: -0.1700
Data Index: 392067 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.5511. Min Act: -0.1700
Data Index: 5777252 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.5350. Min Act: -0.1700
Data Index: 7761449 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.5188. Min Act: -0.1700
Data Index: 5348322 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.5350. Min Act: -0.1700
Data Index: 4452037 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.5350. Min Act: -0.1700
Data Index: 5291439 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.5350. Min Act: -0.1700
Data Index: 4646295 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.5350. Min Act: -0.1700
Data Index: 6512321 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.5350. Min Act: -0.1700
Data Index: 2580435 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.5188. Min Act: -0.1700
Data Index: 4714268 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.5188. Min Act: -0.1700
Data Index: 2831616 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.5188. Min Act: -0.1700
Data Index: 5594580 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.5188. Min Act: -0.1700
Data Index: 7634088 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19