Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2045 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.7302. Min Act: -0.1700
Data Index: 6708272 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.6052. Min Act: -0.1700
Data Index: 3839364 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.5427. Min Act: -0.1700
Data Index: 8207973 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.5115. Min Act: -0.1700
Data Index: 1692664 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.4802. Min Act: -0.1700
Data Index: 8228423 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.4802. Min Act: -0.1700
Data Index: 7311979 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.4490. Min Act: -0.1700
Data Index: 3971064 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.4177. Min Act: -0.1700
Data Index: 4691012 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.4490. Min Act: -0.1695
Data Index: 1269987 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.3240. Min Act: -0.1698
Data Index: 5578858 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.3240. Min Act: -0.1700
Data Index: 498494 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.2927. Min Act: -0.1700
Data Index: 4964950 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.2927. Min Act: -0.1700
Data Index: 2349979 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.2927. Min Act: -0.1699
Data Index: 3788388 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.2927. Min Act: -0.1700
Data Index: 1949010 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.2927. Min Act: -0.1700
Data Index: 2856311 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.2615. Min Act: -0.1699
Data Index: 8110722 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.2302. Min Act: -0.1700
Data Index: 5025208 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.1990. Min Act: -0.1699
Data Index: 5918249 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7302. Min Range: -6.7302
Max Act: 6.2302. Min Act: -0.1700
Data Index: 2586426 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19