Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3264 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.5800. Min Act: -0.1700
Data Index: 377266 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.5487. Min Act: -0.1700
Data Index: 6562065 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.5174. Min Act: -0.1700
Data Index: 5327465 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.5331. Min Act: -0.1700
Data Index: 3511959 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.5018. Min Act: -0.1700
Data Index: 3281192 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.4704. Min Act: -0.1700
Data Index: 7866853 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.4391. Min Act: -0.1700
Data Index: 4025602 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.4391. Min Act: -0.1700
Data Index: 2445 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.4391. Min Act: -0.1700
Data Index: 6733200 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.4234. Min Act: -0.1700
Data Index: 3226835 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.3921. Min Act: -0.1700
Data Index: 5660507 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.3921. Min Act: -0.1700
Data Index: 807011 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.3921. Min Act: -0.1700
Data Index: 4281149 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.3921. Min Act: -0.1700
Data Index: 7673159 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.3764. Min Act: -0.1700
Data Index: 6818090 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.3607. Min Act: -0.1700
Data Index: 6645635 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.3921. Min Act: -0.1700
Data Index: 6967400 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.3450. Min Act: -0.1700
Data Index: 4192543 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.3450. Min Act: -0.1700
Data Index: 6568765 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5800. Min Range: -3.5800
Max Act: 3.3450. Min Act: -0.1700
Data Index: 4847139 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19