Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3326 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.2430. Min Act: -0.1700
Data Index: 2715549 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.2264. Min Act: -0.1700
Data Index: 1110599 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.1933. Min Act: -0.1700
Data Index: 4740184 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.1933. Min Act: -0.1700
Data Index: 929025 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.1766. Min Act: -0.1700
Data Index: 7326225 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.1766. Min Act: -0.1700
Data Index: 8613807 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.1766. Min Act: -0.1700
Data Index: 3943979 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.1933. Min Act: -0.1700
Data Index: 2726536 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.1600. Min Act: -0.1700
Data Index: 2337419 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.1433. Min Act: -0.1700
Data Index: 5180350 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.1600. Min Act: -0.1700
Data Index: 6524797 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.1600. Min Act: -0.1700
Data Index: 922679 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.1600. Min Act: -0.1700
Data Index: 1275338 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.1600. Min Act: -0.1700
Data Index: 3092798 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.1600. Min Act: -0.1700
Data Index: 6857905 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.1600. Min Act: -0.1700
Data Index: 6745204 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.1433. Min Act: -0.1700
Data Index: 3572785 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.1266. Min Act: -0.1700
Data Index: 2414728 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.1600. Min Act: -0.1700
Data Index: 3283345 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2430. Min Range: -2.2430
Max Act: 2.1433. Min Act: -0.1700
Data Index: 4053920 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19