Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1976 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.5990. Min Act: -0.1700
Data Index: 937060 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.6303. Min Act: -0.1700
Data Index: 4958972 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.5990. Min Act: -0.1700
Data Index: 7410088 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.5678. Min Act: -0.1700
Data Index: 1404164 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.5053. Min Act: -0.1700
Data Index: 4090319 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.5053. Min Act: -0.1700
Data Index: 4212636 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.4428. Min Act: -0.1700
Data Index: 8725260 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.4115. Min Act: -0.1700
Data Index: 1395910 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.3803. Min Act: -0.1700
Data Index: 6521752 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.3490. Min Act: -0.1700
Data Index: 3354978 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.3178. Min Act: -0.1700
Data Index: 7196763 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.2865. Min Act: -0.1700
Data Index: 4190149 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.3178. Min Act: -0.1700
Data Index: 7042505 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.3178. Min Act: -0.1700
Data Index: 7999032 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.3490. Min Act: -0.1700
Data Index: 2516299 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.3178. Min Act: -0.1700
Data Index: 7347255 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.2865. Min Act: -0.1700
Data Index: 689037 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.2865. Min Act: -0.1700
Data Index: 7798028 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.2865. Min Act: -0.1700
Data Index: 8244443 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.2553. Min Act: -0.1700
Data Index: 8569767 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19