Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5104 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.3625. Min Act: -0.1700
Data Index: 7908376 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.2998. Min Act: -0.1700
Data Index: 144727 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.2527. Min Act: -0.1700
Data Index: 144726 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.2527. Min Act: -0.1700
Data Index: 122656 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.2212. Min Act: -0.1700
Data Index: 176231 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.2212. Min Act: -0.1700
Data Index: 5896059 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.2212. Min Act: -0.1700
Data Index: 2160735 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.1740. Min Act: -0.1700
Data Index: 144729 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.1583. Min Act: -0.1700
Data Index: 3479476 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.1583. Min Act: -0.1700
Data Index: 7547272 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.1583. Min Act: -0.1700
Data Index: 5055728 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.1426. Min Act: -0.1700
Data Index: 6710109 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.1111. Min Act: -0.1700
Data Index: 1594987 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.1111. Min Act: -0.1700
Data Index: 2951479 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.1111. Min Act: -0.1700
Data Index: 4957859 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.0953. Min Act: -0.1700
Data Index: 1714948 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.1111. Min Act: -0.1700
Data Index: 1373591 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.0953. Min Act: -0.1700
Data Index: 6135495 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.0953. Min Act: -0.1700
Data Index: 3268690 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3625. Min Range: -3.3625
Max Act: 3.0953. Min Act: -0.1700
Data Index: 2696368 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19