Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1305 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9628. Min Act: -0.1700
Data Index: 2811020 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9628. Min Act: -0.1700
Data Index: 7550448 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9628. Min Act: -0.1700
Data Index: 1187782 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9628. Min Act: -0.1700
Data Index: 6024272 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9628. Min Act: -0.1700
Data Index: 1324859 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9315. Min Act: -0.1700
Data Index: 1470958 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9315. Min Act: -0.1700
Data Index: 1212466 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9315. Min Act: -0.1700
Data Index: 2694645 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9003. Min Act: -0.1700
Data Index: 8430683 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9003. Min Act: -0.1700
Data Index: 661660 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9003. Min Act: -0.1700
Data Index: 8354433 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9003. Min Act: -0.1700
Data Index: 6956028 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9003. Min Act: -0.1700
Data Index: 6848898 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9003. Min Act: -0.1700
Data Index: 6440141 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9003. Min Act: -0.1700
Data Index: 1934246 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9003. Min Act: -0.1700
Data Index: 1861594 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9003. Min Act: -0.1700
Data Index: 1750949 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9003. Min Act: -0.1700
Data Index: 5873092 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9003. Min Act: -0.1700
Data Index: 5035525 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9628. Min Range: -3.9628
Max Act: 3.9003. Min Act: -0.1700
Data Index: 3280606 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19