Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3255 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.3817. Min Act: -0.1700
Data Index: 853218 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.3190. Min Act: -0.1700
Data Index: 1019070 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.3503. Min Act: -0.1700
Data Index: 7702830 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.3190. Min Act: -0.1700
Data Index: 7654956 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.3190. Min Act: -0.1700
Data Index: 4352702 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.3190. Min Act: -0.1700
Data Index: 1769560 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.3190. Min Act: -0.1700
Data Index: 1721860 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.3503. Min Act: -0.1700
Data Index: 1626249 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.3503. Min Act: -0.1700
Data Index: 6098678 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.3190. Min Act: -0.1700
Data Index: 3768079 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.3503. Min Act: -0.1699
Data Index: 3752380 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.3503. Min Act: -0.1700
Data Index: 7844169 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.3503. Min Act: -0.1700
Data Index: 3531437 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.3190. Min Act: -0.1700
Data Index: 6049200 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.3190. Min Act: -0.1700
Data Index: 6373843 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.3190. Min Act: -0.1700
Data Index: 638287 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.3190. Min Act: -0.1700
Data Index: 6261108 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.3190. Min Act: -0.1700
Data Index: 6649983 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.2876. Min Act: -0.1700
Data Index: 7257524 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3817. Min Range: -3.3817
Max Act: 3.3190. Min Act: -0.1700
Data Index: 7750436 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19