Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1464 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.5842. Min Act: -0.1700
Data Index: 7318219 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.5196. Min Act: -0.1700
Data Index: 6456132 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.5034. Min Act: -0.1700
Data Index: 4956488 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.4872. Min Act: -0.1700
Data Index: 2497796 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.4872. Min Act: -0.1700
Data Index: 3054424 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.4547. Min Act: -0.1700
Data Index: 6674247 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.4547. Min Act: -0.1700
Data Index: 234970 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.4547. Min Act: -0.1699
Data Index: 3331558 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.4385. Min Act: -0.1700
Data Index: 6816977 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.4222. Min Act: -0.1700
Data Index: 7940256 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.4222. Min Act: -0.1700
Data Index: 6526125 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.4222. Min Act: -0.1700
Data Index: 6646531 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.4222. Min Act: -0.1700
Data Index: 1658120 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.4222. Min Act: -0.1700
Data Index: 4821472 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.4385. Min Act: -0.1700
Data Index: 2519423 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.4059. Min Act: -0.1700
Data Index: 27458 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.4059. Min Act: -0.1700
Data Index: 7476415 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.3896. Min Act: -0.1700
Data Index: 3212322 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.3896. Min Act: -0.1700
Data Index: 6858580 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5842. Min Range: -2.5842
Max Act: 2.3896. Min Act: -0.1700
Data Index: 2497788 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19