Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3306 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.8500. Min Act: -0.1700
Data Index: 627245 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.7250. Min Act: -0.1700
Data Index: 788568 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.7250. Min Act: -0.1700
Data Index: 6207668 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.5687. Min Act: -0.1700
Data Index: 3622998 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.4125. Min Act: -0.1700
Data Index: 7910484 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.3500. Min Act: -0.1700
Data Index: 7052060 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.2562. Min Act: -0.1700
Data Index: 1254790 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.2562. Min Act: -0.1700
Data Index: 998476 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.1937. Min Act: -0.1700
Data Index: 2321630 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.1937. Min Act: -0.1700
Data Index: 1765337 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.1625. Min Act: -0.1700
Data Index: 708570 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.1625. Min Act: -0.1700
Data Index: 6742413 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.1312. Min Act: -0.1700
Data Index: 1943555 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.1312. Min Act: -0.1700
Data Index: 4205735 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.1000. Min Act: -0.1700
Data Index: 5625357 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.1000. Min Act: -0.1700
Data Index: 1252150 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.1000. Min Act: -0.1700
Data Index: 2003084 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.0687. Min Act: -0.1700
Data Index: 5537624 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.0062. Min Act: -0.1700
Data Index: 8798707 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8500. Min Range: -7.8500
Max Act: 7.0062. Min Act: -0.1700
Data Index: 3487424 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19