Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4381 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.4678. Min Act: -0.1700
Data Index: 8766839 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.4365. Min Act: -0.1700
Data Index: 689352 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.4365. Min Act: -0.1700
Data Index: 5162136 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.4053. Min Act: -0.1700
Data Index: 5699717 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.3115. Min Act: -0.1700
Data Index: 3363990 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.3115. Min Act: -0.1700
Data Index: 8047571 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.2803. Min Act: -0.1700
Data Index: 2426649 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.2803. Min Act: -0.1700
Data Index: 2513235 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.2490. Min Act: -0.1700
Data Index: 3243588 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.2490. Min Act: -0.1700
Data Index: 6169655 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.2490. Min Act: -0.1700
Data Index: 74259 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.2490. Min Act: -0.1700
Data Index: 4236749 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.2490. Min Act: -0.1700
Data Index: 4291667 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.2490. Min Act: -0.1700
Data Index: 4214708 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.2490. Min Act: -0.1700
Data Index: 5151020 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.2490. Min Act: -0.1700
Data Index: 5948624 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.2490. Min Act: -0.1700
Data Index: 2537413 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.2490. Min Act: -0.1700
Data Index: 2583604 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.2490. Min Act: -0.1700
Data Index: 8192413 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4678. Min Range: -4.4678
Max Act: 4.2177. Min Act: -0.1700
Data Index: 5438682 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19