Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5385 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.8223. Min Act: -0.1700
Data Index: 3949059 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.7441. Min Act: -0.1700
Data Index: 3700419 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.7128. Min Act: -0.1700
Data Index: 4914099 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.7285. Min Act: -0.1700
Data Index: 8148504 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.6816. Min Act: -0.1700
Data Index: 8078667 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.6972. Min Act: -0.1700
Data Index: 5228500 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.6972. Min Act: -0.1700
Data Index: 8170705 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.6503. Min Act: -0.1700
Data Index: 4793447 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.6346. Min Act: -0.1700
Data Index: 2812245 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.6503. Min Act: -0.1700
Data Index: 2795129 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.6190. Min Act: -0.1700
Data Index: 5453201 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.6190. Min Act: -0.1700
Data Index: 2473531 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.6190. Min Act: -0.1700
Data Index: 3245671 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.6033. Min Act: -0.1700
Data Index: 7354056 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.6033. Min Act: -0.1700
Data Index: 924686 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.5564. Min Act: -0.1700
Data Index: 231941 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.5564. Min Act: -0.1700
Data Index: 7316236 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.5564. Min Act: -0.1700
Data Index: 5237938 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.5720. Min Act: -0.1700
Data Index: 2053584 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8223. Min Range: -3.8223
Max Act: 3.5564. Min Act: -0.1700
Data Index: 3006332 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19