Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3453 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.5374. Min Act: -0.1700
Data Index: 4144290 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.4748. Min Act: -0.1700
Data Index: 722858 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.4435. Min Act: -0.1700
Data Index: 2899919 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.3807. Min Act: -0.1700
Data Index: 1861872 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.3807. Min Act: -0.1700
Data Index: 7770011 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.3807. Min Act: -0.1700
Data Index: 193188 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.3180. Min Act: -0.1700
Data Index: 4873458 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.3494. Min Act: -0.1700
Data Index: 7770012 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.3023. Min Act: -0.1700
Data Index: 3553316 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.3023. Min Act: -0.1700
Data Index: 4816723 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.3180. Min Act: -0.1700
Data Index: 4250066 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.2866. Min Act: -0.1700
Data Index: 3918786 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.2866. Min Act: -0.1700
Data Index: 5383386 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.2866. Min Act: -0.1700
Data Index: 2122029 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.2866. Min Act: -0.1700
Data Index: 6484205 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.2709. Min Act: -0.1700
Data Index: 5783284 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.2866. Min Act: -0.1700
Data Index: 7138697 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.2552. Min Act: -0.1700
Data Index: 3181870 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.2552. Min Act: -0.1700
Data Index: 6005088 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5374. Min Range: -3.5374
Max Act: 3.2395. Min Act: -0.1700
Data Index: 4789034 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19