Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1964 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5046. Min Range: -6.5046
Max Act: 6.5046. Min Act: -0.1700
Data Index: 499563 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5046. Min Range: -6.5046
Max Act: 6.5046. Min Act: -0.1700
Data Index: 3582817 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5046. Min Range: -6.5046
Max Act: 6.5046. Min Act: -0.1700
Data Index: 6773990 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5046. Min Range: -6.5046
Max Act: 6.5046. Min Act: -0.1700
Data Index: 3914379 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5046. Min Range: -6.5046
Max Act: 6.3484. Min Act: -0.1700
Data Index: 3100658 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5046. Min Range: -6.5046
Max Act: 6.3484. Min Act: -0.1700
Data Index: 8026041 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5046. Min Range: -6.5046
Max Act: 6.3171. Min Act: -0.1700
Data Index: 7038840 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5046. Min Range: -6.5046
Max Act: 6.2234. Min Act: -0.1700
Data Index: 8539668 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5046. Min Range: -6.5046
Max Act: 6.1609. Min Act: -0.1700
Data Index: 8156133 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5046. Min Range: -6.5046
Max Act: 6.0984. Min Act: -0.1700
Data Index: 5360721 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5046. Min Range: -6.5046
Max Act: 6.0671. Min Act: -0.1700
Data Index: 342483 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5046. Min Range: -6.5046
Max Act: 6.0359. Min Act: -0.1700
Data Index: 5457998 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5046. Min Range: -6.5046
Max Act: 6.0359. Min Act: -0.1700
Data Index: 1230822 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5046. Min Range: -6.5046
Max Act: 6.0046. Min Act: -0.1700
Data Index: 1224272 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5046. Min Range: -6.5046
Max Act: 5.9421. Min Act: -0.1700
Data Index: 5087999 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5046. Min Range: -6.5046
Max Act: 5.9109. Min Act: -0.1700
Data Index: 4197448 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5046. Min Range: -6.5046
Max Act: 5.9109. Min Act: -0.1700
Data Index: 8316729 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5046. Min Range: -6.5046
Max Act: 5.9109. Min Act: -0.1700
Data Index: 1040462 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5046. Min Range: -6.5046
Max Act: 5.8796. Min Act: -0.1700
Data Index: 5148046 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5046. Min Range: -6.5046
Max Act: 5.8796. Min Act: -0.1700
Data Index: 4692596 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19