Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 452 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.2619. Min Act: -0.1700
Data Index: 7745328 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.2306. Min Act: -0.1700
Data Index: 1378053 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.2306. Min Act: -0.1700
Data Index: 1642529 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.2306. Min Act: -0.1700
Data Index: 8317817 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.2306. Min Act: -0.1700
Data Index: 8459266 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.2306. Min Act: -0.1700
Data Index: 7745320 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.2619. Min Act: -0.1700
Data Index: 7745326 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.2306. Min Act: -0.1700
Data Index: 5264447 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.1681. Min Act: -0.1700
Data Index: 7745327 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.1681. Min Act: -0.1700
Data Index: 132706 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.1369. Min Act: -0.1700
Data Index: 7732145 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.1369. Min Act: -0.1700
Data Index: 4563761 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.1369. Min Act: -0.1700
Data Index: 2185822 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.1369. Min Act: -0.1700
Data Index: 4025027 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.1369. Min Act: -0.1700
Data Index: 8452385 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.1056. Min Act: -0.1700
Data Index: 3618371 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.0744. Min Act: -0.1700
Data Index: 7462043 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.0744. Min Act: -0.1700
Data Index: 6005668 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.0744. Min Act: -0.1700
Data Index: 7745334 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2619. Min Range: -5.2619
Max Act: 5.0431. Min Act: -0.1700
Data Index: 4788904 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19