Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5800 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8883. Min Range: -10.8883
Max Act: 10.8883. Min Act: -0.1700
Data Index: 1505663 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8883. Min Range: -10.8883
Max Act: 10.4508. Min Act: -0.1700
Data Index: 463307 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8883. Min Range: -10.8883
Max Act: 10.2008. Min Act: -0.1700
Data Index: 7257299 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8883. Min Range: -10.8883
Max Act: 10.1383. Min Act: -0.1700
Data Index: 4235681 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8883. Min Range: -10.8883
Max Act: 10.0758. Min Act: -0.1700
Data Index: 1633711 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8883. Min Range: -10.8883
Max Act: 10.0758. Min Act: -0.1700
Data Index: 3970722 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8883. Min Range: -10.8883
Max Act: 9.7633. Min Act: -0.1700
Data Index: 7252821 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8883. Min Range: -10.8883
Max Act: 9.7633. Min Act: -0.1700
Data Index: 1632281 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8883. Min Range: -10.8883
Max Act: 9.7633. Min Act: -0.1700
Data Index: 2444525 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8883. Min Range: -10.8883
Max Act: 9.7633. Min Act: -0.1700
Data Index: 819293 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8883. Min Range: -10.8883
Max Act: 9.7633. Min Act: -0.1700
Data Index: 8741564 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8883. Min Range: -10.8883
Max Act: 9.7633. Min Act: -0.1700
Data Index: 3163262 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8883. Min Range: -10.8883
Max Act: 9.7633. Min Act: -0.1700
Data Index: 4202925 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8883. Min Range: -10.8883
Max Act: 9.7008. Min Act: -0.1700
Data Index: 2846144 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8883. Min Range: -10.8883
Max Act: 9.7008. Min Act: -0.1700
Data Index: 1966695 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8883. Min Range: -10.8883
Max Act: 9.7008. Min Act: -0.1700
Data Index: 2465279 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8883. Min Range: -10.8883
Max Act: 9.7008. Min Act: -0.1700
Data Index: 2933676 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8883. Min Range: -10.8883
Max Act: 9.6383. Min Act: -0.1700
Data Index: 6308817 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8883. Min Range: -10.8883
Max Act: 9.6383. Min Act: -0.1700
Data Index: 5160138 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8883. Min Range: -10.8883
Max Act: 9.6383. Min Act: -0.1700
Data Index: 1011077 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19