Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1914 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5576. Min Range: -8.5576
Max Act: 8.5576. Min Act: -0.1700
Data Index: 8530966 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5576. Min Range: -8.5576
Max Act: 8.2451. Min Act: -0.1700
Data Index: 1056742 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5576. Min Range: -8.5576
Max Act: 8.2451. Min Act: -0.1700
Data Index: 1836181 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5576. Min Range: -8.5576
Max Act: 7.9638. Min Act: -0.1700
Data Index: 5677515 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5576. Min Range: -8.5576
Max Act: 7.9638. Min Act: -0.1700
Data Index: 5841477 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5576. Min Range: -8.5576
Max Act: 7.9326. Min Act: -0.1700
Data Index: 5047000 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5576. Min Range: -8.5576
Max Act: 7.9326. Min Act: -0.1700
Data Index: 7935406 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5576. Min Range: -8.5576
Max Act: 7.9013. Min Act: -0.1700
Data Index: 2086588 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5576. Min Range: -8.5576
Max Act: 7.9013. Min Act: -0.1700
Data Index: 4431966 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5576. Min Range: -8.5576
Max Act: 7.8701. Min Act: -0.1700
Data Index: 1732595 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5576. Min Range: -8.5576
Max Act: 7.8388. Min Act: -0.1700
Data Index: 3193227 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5576. Min Range: -8.5576
Max Act: 7.7763. Min Act: -0.1699
Data Index: 149895 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5576. Min Range: -8.5576
Max Act: 7.8076. Min Act: -0.1700
Data Index: 4472237 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5576. Min Range: -8.5576
Max Act: 7.8076. Min Act: -0.1700
Data Index: 8585182 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5576. Min Range: -8.5576
Max Act: 7.7763. Min Act: -0.1700
Data Index: 2927666 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5576. Min Range: -8.5576
Max Act: 7.7138. Min Act: -0.1700
Data Index: 3798883 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5576. Min Range: -8.5576
Max Act: 7.6826. Min Act: -0.1700
Data Index: 4307587 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5576. Min Range: -8.5576
Max Act: 7.6826. Min Act: -0.1700
Data Index: 4678538 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5576. Min Range: -8.5576
Max Act: 7.6513. Min Act: -0.1700
Data Index: 2996498 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5576. Min Range: -8.5576
Max Act: 7.6201. Min Act: -0.1700
Data Index: 5241214 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19