Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3285 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.6688. Min Act: -0.1700
Data Index: 5608195 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.6688. Min Act: -0.1700
Data Index: 2525857 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.6062. Min Act: -0.1700
Data Index: 3696913 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.6375. Min Act: -0.1700
Data Index: 3530937 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.6375. Min Act: -0.1700
Data Index: 2963698 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.6062. Min Act: -0.1700
Data Index: 6876795 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.5749. Min Act: -0.1700
Data Index: 7913017 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.6062. Min Act: -0.1700
Data Index: 1253986 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.6062. Min Act: -0.1700
Data Index: 7646626 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.6062. Min Act: -0.1700
Data Index: 3078492 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.6062. Min Act: -0.1700
Data Index: 7042568 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.6062. Min Act: -0.1700
Data Index: 1363757 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.6062. Min Act: -0.1700
Data Index: 185348 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.6062. Min Act: -0.1700
Data Index: 6263726 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.6062. Min Act: -0.1700
Data Index: 6001146 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.6375. Min Act: -0.1700
Data Index: 5846840 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.6062. Min Act: -0.1700
Data Index: 1998627 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.6062. Min Act: -0.1700
Data Index: 406063 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.5749. Min Act: -0.1700
Data Index: 5459174 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6688. Min Range: -3.6688
Max Act: 3.6062. Min Act: -0.1700
Data Index: 1445877 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19