Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.5398. Min Act: -0.1700
Data Index: 5928936 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.5398. Min Act: -0.1700
Data Index: 288462 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.5398. Min Act: -0.1700
Data Index: 8197074 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.5398. Min Act: -0.1700
Data Index: 5056378 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.5085. Min Act: -0.1700
Data Index: 7865665 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.5085. Min Act: -0.1700
Data Index: 2517778 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.5085. Min Act: -0.1700
Data Index: 1478246 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.5085. Min Act: -0.1700
Data Index: 882870 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.4772. Min Act: -0.1700
Data Index: 4772403 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.4772. Min Act: -0.1700
Data Index: 1456486 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.4772. Min Act: -0.1700
Data Index: 5592189 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.4772. Min Act: -0.1700
Data Index: 71711 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.4772. Min Act: -0.1700
Data Index: 3878502 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.4772. Min Act: -0.1700
Data Index: 1875426 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.4772. Min Act: -0.1700
Data Index: 7902393 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.4772. Min Act: -0.1700
Data Index: 6643947 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.4772. Min Act: -0.1700
Data Index: 2808248 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.4459. Min Act: -0.1700
Data Index: 4800265 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.4459. Min Act: -0.1700
Data Index: 4138281 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.4459. Min Act: -0.1700
Data Index: 5780553 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19