Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5860 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.8038. Min Act: -0.1700
Data Index: 368051 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.5851. Min Act: -0.1700
Data Index: 1580703 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.5226. Min Act: -0.1700
Data Index: 6002941 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.5226. Min Act: -0.1700
Data Index: 2878800 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.4913. Min Act: -0.1700
Data Index: 3784741 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.4601. Min Act: -0.1700
Data Index: 3885830 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.3663. Min Act: -0.1700
Data Index: 7778865 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.3351. Min Act: -0.1700
Data Index: 8726233 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.3351. Min Act: -0.1700
Data Index: 6002940 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.3351. Min Act: -0.1700
Data Index: 368050 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.3038. Min Act: -0.1700
Data Index: 6960061 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.3038. Min Act: -0.1700
Data Index: 8726232 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.2413. Min Act: -0.1700
Data Index: 4807149 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.2101. Min Act: -0.1700
Data Index: 2019782 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.2101. Min Act: -0.1700
Data Index: 871641 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.2413. Min Act: -0.1700
Data Index: 3269488 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.2101. Min Act: -0.1700
Data Index: 6864578 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.2101. Min Act: -0.1700
Data Index: 793487 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.1476. Min Act: -0.1700
Data Index: 3161867 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8038. Min Range: -6.8038
Max Act: 6.1476. Min Act: -0.1700
Data Index: 1718772 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19