Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3145 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.4492. Min Act: -0.1700
Data Index: 7903288 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.2304. Min Act: -0.1700
Data Index: 939681 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.2304. Min Act: -0.1700
Data Index: 222720 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.2929. Min Act: -0.1700
Data Index: 7002717 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.2304. Min Act: -0.1700
Data Index: 1268287 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.1992. Min Act: -0.1700
Data Index: 7625703 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.1367. Min Act: -0.1700
Data Index: 2681424 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.1367. Min Act: -0.1700
Data Index: 8741965 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.1367. Min Act: -0.1700
Data Index: 489867 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.1367. Min Act: -0.1700
Data Index: 2650435 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.0742. Min Act: -0.1700
Data Index: 5584817 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.0742. Min Act: -0.1700
Data Index: 2698583 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.0742. Min Act: -0.1700
Data Index: 888517 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.0742. Min Act: -0.1700
Data Index: 2655945 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.0429. Min Act: -0.1700
Data Index: 1060844 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.0429. Min Act: -0.1700
Data Index: 6190289 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.0429. Min Act: -0.1700
Data Index: 1452144 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.0117. Min Act: -0.1700
Data Index: 5713735 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4492. Min Range: -6.4492
Max Act: 5.9804. Min Act: -0.1700
Data Index: 1497978 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4492. Min Range: -6.4492
Max Act: 5.9492. Min Act: -0.1700
Data Index: 2213878 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19