Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4320 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8527. Min Range: -6.8527
Max Act: 6.8527. Min Act: -0.1700
Data Index: 3620873 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8527. Min Range: -6.8527
Max Act: 6.3527. Min Act: -0.1700
Data Index: 4215929 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8527. Min Range: -6.8527
Max Act: 6.2277. Min Act: -0.1700
Data Index: 6779800 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8527. Min Range: -6.8527
Max Act: 6.1340. Min Act: -0.1700
Data Index: 7162610 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8527. Min Range: -6.8527
Max Act: 5.9777. Min Act: -0.1700
Data Index: 2585079 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8527. Min Range: -6.8527
Max Act: 5.8527. Min Act: -0.1700
Data Index: 1789870 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8527. Min Range: -6.8527
Max Act: 5.8215. Min Act: -0.1700
Data Index: 7202636 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8527. Min Range: -6.8527
Max Act: 5.7277. Min Act: -0.1700
Data Index: 5181 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8527. Min Range: -6.8527
Max Act: 5.7277. Min Act: -0.1700
Data Index: 2408027 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8527. Min Range: -6.8527
Max Act: 5.7277. Min Act: -0.1700
Data Index: 7883519 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8527. Min Range: -6.8527
Max Act: 5.6965. Min Act: -0.1700
Data Index: 72588 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8527. Min Range: -6.8527
Max Act: 5.6340. Min Act: -0.1700
Data Index: 1374414 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8527. Min Range: -6.8527
Max Act: 5.6340. Min Act: -0.1700
Data Index: 8552392 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8527. Min Range: -6.8527
Max Act: 5.6027. Min Act: -0.1700
Data Index: 2015473 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8527. Min Range: -6.8527
Max Act: 5.5715. Min Act: -0.1700
Data Index: 6810954 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8527. Min Range: -6.8527
Max Act: 5.5715. Min Act: -0.1700
Data Index: 6779801 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8527. Min Range: -6.8527
Max Act: 5.5715. Min Act: -0.1700
Data Index: 6551273 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8527. Min Range: -6.8527
Max Act: 5.5402. Min Act: -0.1700
Data Index: 3378631 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8527. Min Range: -6.8527
Max Act: 5.5715. Min Act: -0.1700
Data Index: 2198704 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8527. Min Range: -6.8527
Max Act: 5.5402. Min Act: -0.1700
Data Index: 4913727 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19