Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3630 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.2450. Min Act: -0.1699
Data Index: 4375760 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.2138. Min Act: -0.1700
Data Index: 4715126 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.2138. Min Act: -0.1700
Data Index: 3683781 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.1825. Min Act: -0.1700
Data Index: 5189225 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.1825. Min Act: -0.1700
Data Index: 980802 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.1513. Min Act: -0.1700
Data Index: 4580675 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.1513. Min Act: -0.1700
Data Index: 4972175 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.1513. Min Act: -0.1700
Data Index: 1110107 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.1513. Min Act: -0.1700
Data Index: 4405625 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.1513. Min Act: -0.1700
Data Index: 8356078 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.1200. Min Act: -0.1700
Data Index: 1999516 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.0888. Min Act: -0.1700
Data Index: 5093342 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.0888. Min Act: -0.1699
Data Index: 4095851 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.1200. Min Act: -0.1700
Data Index: 4983293 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.0888. Min Act: -0.1700
Data Index: 8083525 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.0888. Min Act: -0.1699
Data Index: 5047580 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.0888. Min Act: -0.1700
Data Index: 5044513 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.0888. Min Act: -0.1700
Data Index: 4393928 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.0888. Min Act: -0.1700
Data Index: 1980992 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.0888. Min Act: -0.1700
Data Index: 4416563 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19