Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4512 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.5682. Min Act: -0.1700
Data Index: 350628 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.5057. Min Act: -0.1700
Data Index: 8381925 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.4744. Min Act: -0.1700
Data Index: 8009547 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.4432. Min Act: -0.1700
Data Index: 2007769 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.4432. Min Act: -0.1700
Data Index: 6639042 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.3182. Min Act: -0.1700
Data Index: 6827643 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.3182. Min Act: -0.1700
Data Index: 4769153 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.3494. Min Act: -0.1700
Data Index: 5859353 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.2869. Min Act: -0.1700
Data Index: 6826860 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.2557. Min Act: -0.1700
Data Index: 6515917 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.2557. Min Act: -0.1700
Data Index: 5249682 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.2557. Min Act: -0.1700
Data Index: 2983694 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.2557. Min Act: -0.1700
Data Index: 6213788 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.2557. Min Act: -0.1700
Data Index: 1676045 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.2557. Min Act: -0.1700
Data Index: 7970696 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.2244. Min Act: -0.1700
Data Index: 683883 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.2244. Min Act: -0.1700
Data Index: 4357521 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.2244. Min Act: -0.1700
Data Index: 7399333 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.2244. Min Act: -0.1700
Data Index: 754349 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5682. Min Range: -4.5682
Max Act: 4.2557. Min Act: -0.1700
Data Index: 8068317 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19