Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3559 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2490. Min Range: -7.2490
Max Act: 7.2490. Min Act: -0.1700
Data Index: 1245190 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.8428. Min Act: -0.1700
Data Index: 7990796 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.8115. Min Act: -0.1700
Data Index: 275647 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.8428. Min Act: -0.1700
Data Index: 7623854 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.7803. Min Act: -0.1700
Data Index: 6983203 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.7490. Min Act: -0.1700
Data Index: 1721897 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.7490. Min Act: -0.1700
Data Index: 4278036 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.7178. Min Act: -0.1700
Data Index: 5736456 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.7178. Min Act: -0.1700
Data Index: 4769151 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.6865. Min Act: -0.1700
Data Index: 6711205 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.6553. Min Act: -0.1700
Data Index: 4161599 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.6553. Min Act: -0.1700
Data Index: 7142110 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.5928. Min Act: -0.1700
Data Index: 110491 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.6240. Min Act: -0.1700
Data Index: 7871682 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.6240. Min Act: -0.1700
Data Index: 2212059 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.5615. Min Act: -0.1700
Data Index: 7357296 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.5928. Min Act: -0.1700
Data Index: 5013996 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.5928. Min Act: -0.1700
Data Index: 1420533 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.5615. Min Act: -0.1700
Data Index: 2865366 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.5928. Min Act: -0.1700
Data Index: 4848665 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19