Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2531 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.5504. Min Act: -0.1700
Data Index: 5829076 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.2691. Min Act: -0.1700
Data Index: 5724496 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.1754. Min Act: -0.1700
Data Index: 4069587 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.1754. Min Act: -0.1700
Data Index: 7905453 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.1754. Min Act: -0.1700
Data Index: 4456729 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.1129. Min Act: -0.1700
Data Index: 4855363 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.1129. Min Act: -0.1700
Data Index: 2706218 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.0816. Min Act: -0.1700
Data Index: 4421641 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.0816. Min Act: -0.1700
Data Index: 4415629 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.0504. Min Act: -0.1700
Data Index: 5767045 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.0816. Min Act: -0.1700
Data Index: 6815156 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.0504. Min Act: -0.1700
Data Index: 1826125 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.0191. Min Act: -0.1700
Data Index: 3306328 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5504. Min Range: -5.5504
Max Act: 4.9879. Min Act: -0.1700
Data Index: 1325635 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.0191. Min Act: -0.1700
Data Index: 1423525 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5504. Min Range: -5.5504
Max Act: 4.9879. Min Act: -0.1700
Data Index: 558891 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5504. Min Range: -5.5504
Max Act: 4.9879. Min Act: -0.1700
Data Index: 5401879 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5504. Min Range: -5.5504
Max Act: 4.9879. Min Act: -0.1700
Data Index: 1577396 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5504. Min Range: -5.5504
Max Act: 4.9879. Min Act: -0.1700
Data Index: 4346429 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5504. Min Range: -5.5504
Max Act: 4.9879. Min Act: -0.1700
Data Index: 3402161 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19