Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2871 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2352. Min Range: -6.2352
Max Act: 6.2352. Min Act: -0.1700
Data Index: 577443 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2352. Min Range: -6.2352
Max Act: 6.1415. Min Act: -0.1700
Data Index: 6946512 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2352. Min Range: -6.2352
Max Act: 6.1415. Min Act: -0.1700
Data Index: 2401676 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2352. Min Range: -6.2352
Max Act: 6.1415. Min Act: -0.1700
Data Index: 4156436 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2352. Min Range: -6.2352
Max Act: 6.0477. Min Act: -0.1700
Data Index: 1887222 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2352. Min Range: -6.2352
Max Act: 6.0165. Min Act: -0.1700
Data Index: 488201 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.9540. Min Act: -0.1700
Data Index: 4079815 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.9227. Min Act: -0.1700
Data Index: 8781394 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.9227. Min Act: -0.1700
Data Index: 6021767 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.8915. Min Act: -0.1700
Data Index: 6751545 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.8915. Min Act: -0.1700
Data Index: 6985247 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.8602. Min Act: -0.1700
Data Index: 2303383 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.8290. Min Act: -0.1700
Data Index: 4218662 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.7977. Min Act: -0.1700
Data Index: 926608 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.7977. Min Act: -0.1700
Data Index: 1308082 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.7352. Min Act: -0.1700
Data Index: 8145264 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.7665. Min Act: -0.1700
Data Index: 5214935 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.7665. Min Act: -0.1700
Data Index: 5384204 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.7352. Min Act: -0.1700
Data Index: 8184418 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.7040. Min Act: -0.1700
Data Index: 2873297 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19