Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4356 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.6974. Min Act: -0.1700
Data Index: 5457749 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.6349. Min Act: -0.1700
Data Index: 3863563 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.5724. Min Act: -0.1700
Data Index: 6975110 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.5412. Min Act: -0.1700
Data Index: 746445 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.5412. Min Act: -0.1700
Data Index: 2213815 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.4787. Min Act: -0.1700
Data Index: 3859763 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.4787. Min Act: -0.1700
Data Index: 3367594 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.4474. Min Act: -0.1700
Data Index: 2842499 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.3849. Min Act: -0.1700
Data Index: 7310815 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.4162. Min Act: -0.1700
Data Index: 987671 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.3849. Min Act: -0.1700
Data Index: 6532537 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.3849. Min Act: -0.1700
Data Index: 8206746 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.3537. Min Act: -0.1700
Data Index: 2003106 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.3537. Min Act: -0.1700
Data Index: 295448 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.3537. Min Act: -0.1700
Data Index: 7424315 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.3537. Min Act: -0.1700
Data Index: 7720658 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.2912. Min Act: -0.1700
Data Index: 6793301 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.2599. Min Act: -0.1700
Data Index: 4848209 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.2912. Min Act: -0.1700
Data Index: 935827 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6974. Min Range: -5.6974
Max Act: 5.2912. Min Act: -0.1700
Data Index: 1870796 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19