Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1586 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.6015. Min Act: -0.1700
Data Index: 3790581 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.4140. Min Act: -0.1700
Data Index: 4967131 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1952. Min Act: -0.1700
Data Index: 386582 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1327. Min Act: -0.1700
Data Index: 2310676 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1015. Min Act: -0.1700
Data Index: 5402310 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1327. Min Act: -0.1700
Data Index: 917952 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.0702. Min Act: -0.1700
Data Index: 7584833 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.0390. Min Act: -0.1700
Data Index: 7840747 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.0077. Min Act: -0.1700
Data Index: 5003954 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.0077. Min Act: -0.1700
Data Index: 8064635 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9765. Min Act: -0.1700
Data Index: 4612717 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9765. Min Act: -0.1700
Data Index: 3622792 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9765. Min Act: -0.1700
Data Index: 4153967 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9452. Min Act: -0.1700
Data Index: 3665359 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9452. Min Act: -0.1700
Data Index: 2844343 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9452. Min Act: -0.1700
Data Index: 4341953 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9140. Min Act: -0.1700
Data Index: 2539290 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9140. Min Act: -0.1700
Data Index: 2581609 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9140. Min Act: -0.1700
Data Index: 3622791 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.8827. Min Act: -0.1700
Data Index: 5831336 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19