Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5778 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.6938. Min Act: -0.1700
Data Index: 5736886 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.6001. Min Act: -0.1700
Data Index: 3393536 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.3501. Min Act: -0.1700
Data Index: 1840946 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.2876. Min Act: -0.1700
Data Index: 1896735 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.2563. Min Act: -0.1700
Data Index: 6644211 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.2251. Min Act: -0.1700
Data Index: 793800 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.1626. Min Act: -0.1700
Data Index: 2828012 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.1313. Min Act: -0.1700
Data Index: 593329 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.1001. Min Act: -0.1700
Data Index: 2769594 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.1001. Min Act: -0.1700
Data Index: 4622328 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.1001. Min Act: -0.1700
Data Index: 5958101 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.1001. Min Act: -0.1700
Data Index: 3320720 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.0688. Min Act: -0.1700
Data Index: 4885339 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.0688. Min Act: -0.1700
Data Index: 7969429 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.0688. Min Act: -0.1700
Data Index: 821854 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.0688. Min Act: -0.1700
Data Index: 1949913 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.0063. Min Act: -0.1700
Data Index: 7719416 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.0376. Min Act: -0.1700
Data Index: 7409490 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.0063. Min Act: -0.1700
Data Index: 137857 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6938. Min Range: -5.6938
Max Act: 5.0063. Min Act: -0.1700
Data Index: 5251217 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19