Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3058 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.5447. Min Act: -0.1700
Data Index: 3901186 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.5135. Min Act: -0.1700
Data Index: 5482947 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.4197. Min Act: -0.1700
Data Index: 4531382 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.3572. Min Act: -0.1700
Data Index: 5645789 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.3260. Min Act: -0.1700
Data Index: 4903391 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.3572. Min Act: -0.1700
Data Index: 6263753 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.3260. Min Act: -0.1700
Data Index: 3721653 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.3260. Min Act: -0.1700
Data Index: 4739490 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.2947. Min Act: -0.1700
Data Index: 3767830 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.2947. Min Act: -0.1700
Data Index: 6532038 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.2947. Min Act: -0.1700
Data Index: 1289813 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.3260. Min Act: -0.1700
Data Index: 2844840 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.2635. Min Act: -0.1700
Data Index: 276682 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.2635. Min Act: -0.1700
Data Index: 1963159 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.2635. Min Act: -0.1700
Data Index: 6144970 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.2635. Min Act: -0.1700
Data Index: 8151871 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.2322. Min Act: -0.1700
Data Index: 8601500 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.2010. Min Act: -0.1700
Data Index: 4136111 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.2010. Min Act: -0.1700
Data Index: 6631458 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5447. Min Range: -7.5447
Max Act: 7.2322. Min Act: -0.1700
Data Index: 7664795 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19