Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2914 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.6848. Min Act: -0.1700
Data Index: 7700289 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.4661. Min Act: -0.1700
Data Index: 6183482 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.4036. Min Act: -0.1700
Data Index: 3070815 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.4036. Min Act: -0.1700
Data Index: 788506 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.3723. Min Act: -0.1700
Data Index: 8064283 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.3723. Min Act: -0.1700
Data Index: 148361 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.3411. Min Act: -0.1700
Data Index: 8235483 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.3411. Min Act: -0.1700
Data Index: 3139907 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.3411. Min Act: -0.1700
Data Index: 7710259 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.2786. Min Act: -0.1700
Data Index: 3011685 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.2786. Min Act: -0.1700
Data Index: 5971880 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.3098. Min Act: -0.1700
Data Index: 7736225 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.3411. Min Act: -0.1700
Data Index: 1053184 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.2786. Min Act: -0.1700
Data Index: 7097579 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.3098. Min Act: -0.1700
Data Index: 5155366 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.3098. Min Act: -0.1700
Data Index: 3730269 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.2473. Min Act: -0.1700
Data Index: 3251356 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.2473. Min Act: -0.1700
Data Index: 1811659 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.2786. Min Act: -0.1700
Data Index: 2706113 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.2473. Min Act: -0.1700
Data Index: 2332852 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19