Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3403 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6978. Min Act: -0.1700
Data Index: 5049355 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6665. Min Act: -0.1700
Data Index: 376674 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6665. Min Act: -0.1700
Data Index: 8795676 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6665. Min Act: -0.1700
Data Index: 2816035 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6352. Min Act: -0.1700
Data Index: 1167453 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6352. Min Act: -0.1700
Data Index: 4302966 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6352. Min Act: -0.1700
Data Index: 4182960 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6665. Min Act: -0.1700
Data Index: 3792668 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6352. Min Act: -0.1700
Data Index: 1459053 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6352. Min Act: -0.1700
Data Index: 3643254 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6352. Min Act: -0.1700
Data Index: 1153808 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6352. Min Act: -0.1700
Data Index: 2812464 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6352. Min Act: -0.1700
Data Index: 1910546 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6352. Min Act: -0.1700
Data Index: 8207922 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6352. Min Act: -0.1700
Data Index: 349708 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6352. Min Act: -0.1700
Data Index: 6529316 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6039. Min Act: -0.1700
Data Index: 3061168 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6039. Min Act: -0.1700
Data Index: 1252712 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6039. Min Act: -0.1700
Data Index: 196720 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6978. Min Range: -3.6978
Max Act: 3.6039. Min Act: -0.1700
Data Index: 35403 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19