Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2015 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.8947. Min Act: -0.1700
Data Index: 218582 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.8009. Min Act: -0.1700
Data Index: 5918312 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.7697. Min Act: -0.1700
Data Index: 2481313 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.6447. Min Act: -0.1700
Data Index: 7074796 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.6447. Min Act: -0.1700
Data Index: 3642884 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.6447. Min Act: -0.1700
Data Index: 8568768 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.6447. Min Act: -0.1700
Data Index: 5639501 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.6134. Min Act: -0.1700
Data Index: 6436135 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.5197. Min Act: -0.1700
Data Index: 1401309 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.5509. Min Act: -0.1700
Data Index: 7578566 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.5197. Min Act: -0.1700
Data Index: 8722081 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.4884. Min Act: -0.1700
Data Index: 4706894 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.5197. Min Act: -0.1700
Data Index: 5162694 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.5197. Min Act: -0.1700
Data Index: 3039093 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.4884. Min Act: -0.1700
Data Index: 8537234 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.4884. Min Act: -0.1700
Data Index: 5141283 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.4572. Min Act: -0.1700
Data Index: 589413 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.4884. Min Act: -0.1700
Data Index: 2615678 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.4572. Min Act: -0.1700
Data Index: 4615201 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8947. Min Range: -6.8947
Max Act: 6.4259. Min Act: -0.1700
Data Index: 1803706 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19