Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3523 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4632. Min Range: -7.4632
Max Act: 7.4632. Min Act: -0.1700
Data Index: 3489976 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4632. Min Range: -7.4632
Max Act: 7.1820. Min Act: -0.1700
Data Index: 1555328 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4632. Min Range: -7.4632
Max Act: 7.1507. Min Act: -0.1700
Data Index: 871008 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4632. Min Range: -7.4632
Max Act: 7.0257. Min Act: -0.1700
Data Index: 7942090 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4632. Min Range: -7.4632
Max Act: 7.0570. Min Act: -0.1700
Data Index: 3825831 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4632. Min Range: -7.4632
Max Act: 7.0570. Min Act: -0.1700
Data Index: 5302972 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4632. Min Range: -7.4632
Max Act: 6.9632. Min Act: -0.1700
Data Index: 6390597 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4632. Min Range: -7.4632
Max Act: 6.9320. Min Act: -0.1700
Data Index: 7030299 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4632. Min Range: -7.4632
Max Act: 6.9320. Min Act: -0.1700
Data Index: 4224613 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4632. Min Range: -7.4632
Max Act: 6.8382. Min Act: -0.1700
Data Index: 917935 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4632. Min Range: -7.4632
Max Act: 6.8695. Min Act: -0.1700
Data Index: 2124660 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4632. Min Range: -7.4632
Max Act: 6.8070. Min Act: -0.1700
Data Index: 1153205 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4632. Min Range: -7.4632
Max Act: 6.7757. Min Act: -0.1700
Data Index: 2724785 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4632. Min Range: -7.4632
Max Act: 6.7757. Min Act: -0.1700
Data Index: 1124494 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4632. Min Range: -7.4632
Max Act: 6.7757. Min Act: -0.1700
Data Index: 7333502 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4632. Min Range: -7.4632
Max Act: 6.7757. Min Act: -0.1700
Data Index: 1007530 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4632. Min Range: -7.4632
Max Act: 6.7445. Min Act: -0.1700
Data Index: 7287865 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4632. Min Range: -7.4632
Max Act: 6.7445. Min Act: -0.1700
Data Index: 3405610 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4632. Min Range: -7.4632
Max Act: 6.6820. Min Act: -0.1700
Data Index: 5335003 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4632. Min Range: -7.4632
Max Act: 6.6820. Min Act: -0.1700
Data Index: 1013381 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19