Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2545 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.9074. Min Act: -0.1700
Data Index: 1647171 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.8732. Min Act: -0.1700
Data Index: 1761431 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.8561. Min Act: -0.1700
Data Index: 3133626 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.8218. Min Act: -0.1700
Data Index: 6247610 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.8390. Min Act: -0.1700
Data Index: 3487214 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.8218. Min Act: -0.1700
Data Index: 1031100 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.8218. Min Act: -0.1700
Data Index: 67564 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.8218. Min Act: -0.1700
Data Index: 1244550 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.8047. Min Act: -0.1700
Data Index: 2734244 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.8047. Min Act: -0.1700
Data Index: 5140852 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.8047. Min Act: -0.1700
Data Index: 3969502 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.8047. Min Act: -0.1700
Data Index: 276117 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.8047. Min Act: -0.1700
Data Index: 778689 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.7874. Min Act: -0.1700
Data Index: 5109698 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.7874. Min Act: -0.1700
Data Index: 4163074 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.7874. Min Act: -0.1700
Data Index: 2518661 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.7702. Min Act: -0.1700
Data Index: 1500599 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.7530. Min Act: -0.1699
Data Index: 7481517 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.7702. Min Act: -0.1700
Data Index: 6991107 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9074. Min Range: -1.9074
Max Act: 1.7702. Min Act: -0.1700
Data Index: 1780840 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19