Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 0 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4984. Min Range: -8.4984
Max Act: 8.4984. Min Act: -0.1700
Data Index: 5736286 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4984. Min Range: -8.4984
Max Act: 7.9672. Min Act: -0.1700
Data Index: 5736282 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4984. Min Range: -8.4984
Max Act: 7.0297. Min Act: -0.1700
Data Index: 6352207 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4984. Min Range: -8.4984
Max Act: 7.0297. Min Act: -0.1700
Data Index: 6578396 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4984. Min Range: -8.4984
Max Act: 7.0297. Min Act: -0.1700
Data Index: 6463105 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4984. Min Range: -8.4984
Max Act: 6.9047. Min Act: -0.1700
Data Index: 7412770 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4984. Min Range: -8.4984
Max Act: 6.9672. Min Act: -0.1700
Data Index: 7677709 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4984. Min Range: -8.4984
Max Act: 6.9359. Min Act: -0.1700
Data Index: 3652312 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4984. Min Range: -8.4984
Max Act: 6.9672. Min Act: -0.1700
Data Index: 5255514 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4984. Min Range: -8.4984
Max Act: 6.9672. Min Act: -0.1700
Data Index: 1963623 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4984. Min Range: -8.4984
Max Act: 6.9672. Min Act: -0.1700
Data Index: 3317182 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4984. Min Range: -8.4984
Max Act: 6.9359. Min Act: -0.1700
Data Index: 3726598 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4984. Min Range: -8.4984
Max Act: 6.9047. Min Act: -0.1700
Data Index: 854722 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4984. Min Range: -8.4984
Max Act: 6.9359. Min Act: -0.1700
Data Index: 7822250 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4984. Min Range: -8.4984
Max Act: 6.8734. Min Act: -0.1700
Data Index: 3994368 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4984. Min Range: -8.4984
Max Act: 6.8734. Min Act: -0.1700
Data Index: 2981130 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4984. Min Range: -8.4984
Max Act: 6.8422. Min Act: -0.1700
Data Index: 7682614 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4984. Min Range: -8.4984
Max Act: 6.9359. Min Act: -0.1700
Data Index: 193757 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4984. Min Range: -8.4984
Max Act: 6.9047. Min Act: -0.1700
Data Index: 6898764 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4984. Min Range: -8.4984
Max Act: 6.9047. Min Act: -0.1700
Data Index: 2105346 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19