Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2724 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.9695. Min Act: -0.1700
Data Index: 1196823 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.9070. Min Act: -0.1700
Data Index: 2457709 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.7819. Min Act: -0.1700
Data Index: 6711228 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.7819. Min Act: -0.1700
Data Index: 8314997 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.7193. Min Act: -0.1700
Data Index: 5433103 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.6881. Min Act: -0.1700
Data Index: 3916236 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.6881. Min Act: -0.1700
Data Index: 2234958 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.6724. Min Act: -0.1700
Data Index: 2134031 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.6724. Min Act: -0.1700
Data Index: 6693721 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.6568. Min Act: -0.1700
Data Index: 2228761 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.6724. Min Act: -0.1700
Data Index: 1121526 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.6568. Min Act: -0.1700
Data Index: 345289 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.6255. Min Act: -0.1700
Data Index: 3088340 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.6411. Min Act: -0.1700
Data Index: 7595744 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.6411. Min Act: -0.1700
Data Index: 2996267 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.6255. Min Act: -0.1700
Data Index: 1748667 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.6255. Min Act: -0.1700
Data Index: 8176818 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.6098. Min Act: -0.1700
Data Index: 906501 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.6098. Min Act: -0.1700
Data Index: 684360 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9695. Min Range: -3.9695
Max Act: 3.6098. Min Act: -0.1700
Data Index: 4759422 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19