Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2678 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6441. Min Range: -6.6441
Max Act: 6.6441. Min Act: -0.1700
Data Index: 8603280 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6441. Min Range: -6.6441
Max Act: 6.5504. Min Act: -0.1700
Data Index: 7615838 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6441. Min Range: -6.6441
Max Act: 6.4566. Min Act: -0.1700
Data Index: 6675838 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6441. Min Range: -6.6441
Max Act: 6.3629. Min Act: -0.1700
Data Index: 311999 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6441. Min Range: -6.6441
Max Act: 6.3629. Min Act: -0.1700
Data Index: 524593 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6441. Min Range: -6.6441
Max Act: 6.3316. Min Act: -0.1700
Data Index: 4751365 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6441. Min Range: -6.6441
Max Act: 6.2691. Min Act: -0.1700
Data Index: 5748360 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6441. Min Range: -6.6441
Max Act: 6.2379. Min Act: -0.1700
Data Index: 5082016 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6441. Min Range: -6.6441
Max Act: 6.2066. Min Act: -0.1700
Data Index: 3437019 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6441. Min Range: -6.6441
Max Act: 6.1754. Min Act: -0.1700
Data Index: 2245115 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6441. Min Range: -6.6441
Max Act: 6.1441. Min Act: -0.1700
Data Index: 4993392 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6441. Min Range: -6.6441
Max Act: 6.1129. Min Act: -0.1700
Data Index: 2960479 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6441. Min Range: -6.6441
Max Act: 6.0816. Min Act: -0.1700
Data Index: 2285671 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6441. Min Range: -6.6441
Max Act: 6.0191. Min Act: -0.1700
Data Index: 8704259 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6441. Min Range: -6.6441
Max Act: 6.0191. Min Act: -0.1700
Data Index: 3921947 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6441. Min Range: -6.6441
Max Act: 6.0191. Min Act: -0.1700
Data Index: 2561644 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6441. Min Range: -6.6441
Max Act: 6.0191. Min Act: -0.1700
Data Index: 272857 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6441. Min Range: -6.6441
Max Act: 6.0191. Min Act: -0.1700
Data Index: 811341 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6441. Min Range: -6.6441
Max Act: 6.0191. Min Act: -0.1700
Data Index: 3024817 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6441. Min Range: -6.6441
Max Act: 5.9879. Min Act: -0.1700
Data Index: 935521 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19