Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3909 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.2863. Min Act: -0.1700
Data Index: 5893074 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.2548. Min Act: -0.1700
Data Index: 2478075 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.2391. Min Act: -0.1700
Data Index: 7916778 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.2391. Min Act: -0.1700
Data Index: 2606725 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.2391. Min Act: -0.1700
Data Index: 4217159 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.2234. Min Act: -0.1700
Data Index: 629291 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.2234. Min Act: -0.1700
Data Index: 8199531 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.2234. Min Act: -0.1700
Data Index: 1982246 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.2391. Min Act: -0.1700
Data Index: 798772 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.2234. Min Act: -0.1700
Data Index: 119637 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.2077. Min Act: -0.1700
Data Index: 4829981 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.2077. Min Act: -0.1700
Data Index: 6152438 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.2077. Min Act: -0.1700
Data Index: 1687379 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.2077. Min Act: -0.1700
Data Index: 5355855 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.1762. Min Act: -0.1700
Data Index: 4292773 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.1920. Min Act: -0.1700
Data Index: 1044056 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.1920. Min Act: -0.1700
Data Index: 3321599 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.1920. Min Act: -0.1700
Data Index: 916184 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.1920. Min Act: -0.1700
Data Index: 5306447 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.1920. Min Act: -0.1700
Data Index: 5187015 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19