Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3778 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.5347. Min Act: -0.1700
Data Index: 7705549 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.5034. Min Act: -0.1700
Data Index: 1209554 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.3784. Min Act: -0.1700
Data Index: 8194585 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.3472. Min Act: -0.1700
Data Index: 528513 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.3159. Min Act: -0.1700
Data Index: 5165420 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.3159. Min Act: -0.1700
Data Index: 4627476 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.2534. Min Act: -0.1700
Data Index: 3830562 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.2222. Min Act: -0.1700
Data Index: 4960192 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.2847. Min Act: -0.1700
Data Index: 4139014 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.2534. Min Act: -0.1700
Data Index: 4659617 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.2534. Min Act: -0.1700
Data Index: 3352400 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.2534. Min Act: -0.1700
Data Index: 7329688 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.2534. Min Act: -0.1700
Data Index: 2074940 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.1909. Min Act: -0.1700
Data Index: 3156333 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.1909. Min Act: -0.1700
Data Index: 831390 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.1909. Min Act: -0.1700
Data Index: 4626395 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.1596. Min Act: -0.1700
Data Index: 4013946 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.1596. Min Act: -0.1700
Data Index: 3971133 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.1596. Min Act: -0.1700
Data Index: 3987162 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5347. Min Range: -4.5347
Max Act: 4.1596. Min Act: -0.1700
Data Index: 4967979 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19