Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5095 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5336. Min Range: -5.5336
Max Act: 5.5336. Min Act: -0.1700
Data Index: 8006750 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5336. Min Range: -5.5336
Max Act: 5.3461. Min Act: -0.1700
Data Index: 8071216 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5336. Min Range: -5.5336
Max Act: 5.1586. Min Act: -0.1700
Data Index: 5012674 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5336. Min Range: -5.5336
Max Act: 5.0023. Min Act: -0.1700
Data Index: 1621519 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5336. Min Range: -5.5336
Max Act: 4.9398. Min Act: -0.1700
Data Index: 7362590 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5336. Min Range: -5.5336
Max Act: 4.9398. Min Act: -0.1700
Data Index: 3461132 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5336. Min Range: -5.5336
Max Act: 4.9398. Min Act: -0.1700
Data Index: 6151103 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5336. Min Range: -5.5336
Max Act: 4.9086. Min Act: -0.1700
Data Index: 4397444 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5336. Min Range: -5.5336
Max Act: 4.9086. Min Act: -0.1700
Data Index: 8489367 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5336. Min Range: -5.5336
Max Act: 4.8773. Min Act: -0.1700
Data Index: 7899245 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5336. Min Range: -5.5336
Max Act: 4.8773. Min Act: -0.1700
Data Index: 7443382 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5336. Min Range: -5.5336
Max Act: 4.8148. Min Act: -0.1700
Data Index: 6888973 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5336. Min Range: -5.5336
Max Act: 4.8461. Min Act: -0.1700
Data Index: 3545930 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5336. Min Range: -5.5336
Max Act: 4.8461. Min Act: -0.1700
Data Index: 5140711 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5336. Min Range: -5.5336
Max Act: 4.8461. Min Act: -0.1700
Data Index: 121834 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5336. Min Range: -5.5336
Max Act: 4.8148. Min Act: -0.1700
Data Index: 8088147 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5336. Min Range: -5.5336
Max Act: 4.8148. Min Act: -0.1700
Data Index: 237161 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5336. Min Range: -5.5336
Max Act: 4.7836. Min Act: -0.1700
Data Index: 99554 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5336. Min Range: -5.5336
Max Act: 4.7523. Min Act: -0.1700
Data Index: 1967041 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5336. Min Range: -5.5336
Max Act: 4.8148. Min Act: -0.1700
Data Index: 1277692 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19