Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 373 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.4411. Min Act: -0.1700
Data Index: 4306588 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.4723. Min Act: -0.1700
Data Index: 7279392 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.3473. Min Act: -0.1700
Data Index: 267326 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.3473. Min Act: -0.1700
Data Index: 5217565 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.3786. Min Act: -0.1700
Data Index: 1708641 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.3786. Min Act: -0.1700
Data Index: 3090791 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.3786. Min Act: -0.1700
Data Index: 571323 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.3473. Min Act: -0.1700
Data Index: 1301037 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.3161. Min Act: -0.1700
Data Index: 1724137 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.2848. Min Act: -0.1700
Data Index: 2685319 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.2536. Min Act: -0.1700
Data Index: 1598382 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.2848. Min Act: -0.1700
Data Index: 3950798 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.2536. Min Act: -0.1700
Data Index: 3032143 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.2848. Min Act: -0.1700
Data Index: 8033240 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.2536. Min Act: -0.1700
Data Index: 6480781 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.2536. Min Act: -0.1700
Data Index: 1670757 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.2848. Min Act: -0.1700
Data Index: 6684691 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.2536. Min Act: -0.1700
Data Index: 1881649 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.2536. Min Act: -0.1700
Data Index: 7155237 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4723. Min Range: -5.4723
Max Act: 5.2536. Min Act: -0.1700
Data Index: 794424 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19