Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 789 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.6841. Min Act: -0.1700
Data Index: 1216130 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.6216. Min Act: -0.1700
Data Index: 542174 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.5278. Min Act: -0.1700
Data Index: 396077 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.4653. Min Act: -0.1700
Data Index: 777226 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.4653. Min Act: -0.1700
Data Index: 5547854 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.4341. Min Act: -0.1700
Data Index: 2345135 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.4341. Min Act: -0.1700
Data Index: 4317856 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.4341. Min Act: -0.1700
Data Index: 347886 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.4341. Min Act: -0.1700
Data Index: 4701782 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.4341. Min Act: -0.1700
Data Index: 7868554 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.4028. Min Act: -0.1700
Data Index: 1662012 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.4028. Min Act: -0.1700
Data Index: 5515596 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.3716. Min Act: -0.1700
Data Index: 4270728 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.3716. Min Act: -0.1700
Data Index: 164626 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.3716. Min Act: -0.1700
Data Index: 6157439 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.3716. Min Act: -0.1700
Data Index: 92970 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.3403. Min Act: -0.1700
Data Index: 878250 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.3403. Min Act: -0.1700
Data Index: 5460466 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.3403. Min Act: -0.1700
Data Index: 1451111 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6841. Min Range: -5.6841
Max Act: 5.3716. Min Act: -0.1700
Data Index: 7784160 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19