Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3344 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.4453. Min Act: -0.1700
Data Index: 2035169 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.3515. Min Act: -0.1700
Data Index: 2428541 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.3203. Min Act: -0.1700
Data Index: 1857500 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.2890. Min Act: -0.1700
Data Index: 2242405 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.2578. Min Act: -0.1700
Data Index: 6955904 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.1953. Min Act: -0.1700
Data Index: 3447050 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.1953. Min Act: -0.1700
Data Index: 4236671 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.1640. Min Act: -0.1700
Data Index: 6647187 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.1640. Min Act: -0.1700
Data Index: 4665835 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.1328. Min Act: -0.1700
Data Index: 8065629 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.1328. Min Act: -0.1700
Data Index: 2411694 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.1015. Min Act: -0.1700
Data Index: 5507536 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.0703. Min Act: -0.1700
Data Index: 556221 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.1015. Min Act: -0.1700
Data Index: 3422069 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.1015. Min Act: -0.1700
Data Index: 8007797 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.1015. Min Act: -0.1700
Data Index: 7348661 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.1015. Min Act: -0.1700
Data Index: 2944438 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.0390. Min Act: -0.1700
Data Index: 816469 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.0703. Min Act: -0.1700
Data Index: 4482816 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4453. Min Range: -7.4453
Max Act: 7.1015. Min Act: -0.1700
Data Index: 1463453 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19