Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1806 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6496. Min Act: -0.1700
Data Index: 4607359 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6496. Min Act: -0.1700
Data Index: 6373521 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6335. Min Act: -0.1700
Data Index: 6470323 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6496. Min Act: -0.1700
Data Index: 3810027 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6496. Min Act: -0.1700
Data Index: 8645616 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6496. Min Act: -0.1700
Data Index: 7258966 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6496. Min Act: -0.1700
Data Index: 3603993 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6496. Min Act: -0.1700
Data Index: 1512912 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6496. Min Act: -0.1700
Data Index: 6746776 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6496. Min Act: -0.1700
Data Index: 6470723 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6335. Min Act: -0.1700
Data Index: 1540712 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6335. Min Act: -0.1700
Data Index: 3804728 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6335. Min Act: -0.1700
Data Index: 1675100 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6335. Min Act: -0.1700
Data Index: 4797532 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6335. Min Act: -0.1700
Data Index: 5015776 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6335. Min Act: -0.1700
Data Index: 5630139 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6335. Min Act: -0.1700
Data Index: 792894 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6335. Min Act: -0.1700
Data Index: 5830871 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6335. Min Act: -0.1700
Data Index: 6298317 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6496. Min Range: -2.6496
Max Act: 2.6335. Min Act: -0.1700
Data Index: 1869208 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19