Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6048 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.4178. Min Act: -0.1700
Data Index: 1774021 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.2615. Min Act: -0.1700
Data Index: 6313316 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.2303. Min Act: -0.1700
Data Index: 2039540 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1678. Min Act: -0.1700
Data Index: 1774022 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1678. Min Act: -0.1700
Data Index: 6366510 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1365. Min Act: -0.1700
Data Index: 2134550 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1053. Min Act: -0.1700
Data Index: 1867584 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1053. Min Act: -0.1700
Data Index: 7970614 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.0427. Min Act: -0.1700
Data Index: 2462218 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.0427. Min Act: -0.1700
Data Index: 6453251 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.0115. Min Act: -0.1700
Data Index: 3560449 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.0115. Min Act: -0.1700
Data Index: 2134567 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.0115. Min Act: -0.1700
Data Index: 2731392 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.0115. Min Act: -0.1700
Data Index: 6360732 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4178. Min Range: -4.4178
Max Act: 3.9802. Min Act: -0.1700
Data Index: 6757714 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4178. Min Range: -4.4178
Max Act: 3.9802. Min Act: -0.1700
Data Index: 1867568 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4178. Min Range: -4.4178
Max Act: 3.9490. Min Act: -0.1700
Data Index: 7533336 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4178. Min Range: -4.4178
Max Act: 3.9490. Min Act: -0.1700
Data Index: 3560469 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4178. Min Range: -4.4178
Max Act: 3.9177. Min Act: -0.1700
Data Index: 2774631 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4178. Min Range: -4.4178
Max Act: 3.9490. Min Act: -0.1700
Data Index: 1867572 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19