Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1268 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.4699. Min Act: -0.1700
Data Index: 4802078 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.2503. Min Act: -0.1700
Data Index: 4405995 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.2031. Min Act: -0.1700
Data Index: 7214521 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.1717. Min Act: -0.1700
Data Index: 42143 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.1874. Min Act: -0.1700
Data Index: 835052 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.1717. Min Act: -0.1700
Data Index: 2938192 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.1402. Min Act: -0.1700
Data Index: 1031685 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.1402. Min Act: -0.1700
Data Index: 6179205 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.1402. Min Act: -0.1700
Data Index: 1492539 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.1559. Min Act: -0.1700
Data Index: 7739902 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.1402. Min Act: -0.1700
Data Index: 450411 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.1402. Min Act: -0.1700
Data Index: 5940810 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.1244. Min Act: -0.1700
Data Index: 509010 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.1402. Min Act: -0.1700
Data Index: 8547453 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.1244. Min Act: -0.1700
Data Index: 2996818 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.1244. Min Act: -0.1700
Data Index: 536076 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.1087. Min Act: -0.1700
Data Index: 8535567 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.1087. Min Act: -0.1700
Data Index: 8161859 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.0771. Min Act: -0.1700
Data Index: 3641220 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4699. Min Range: -3.4699
Max Act: 3.1087. Min Act: -0.1700
Data Index: 3015758 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19