Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 987 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.8806. Min Act: -0.1700
Data Index: 5353967 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.8806. Min Act: -0.1700
Data Index: 7907588 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.3493. Min Act: -0.1700
Data Index: 1822316 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.3493. Min Act: -0.1700
Data Index: 7995838 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.3181. Min Act: -0.1700
Data Index: 1103317 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.2868. Min Act: -0.1700
Data Index: 121746 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.2556. Min Act: -0.1700
Data Index: 4263761 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.2243. Min Act: -0.1700
Data Index: 6536473 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.1618. Min Act: -0.1700
Data Index: 322201 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.1618. Min Act: -0.1700
Data Index: 3261031 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.1618. Min Act: -0.1700
Data Index: 6048909 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.1618. Min Act: -0.1700
Data Index: 173124 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.1618. Min Act: -0.1700
Data Index: 459051 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.1306. Min Act: -0.1700
Data Index: 7583356 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.1618. Min Act: -0.1700
Data Index: 1049022 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.0680. Min Act: -0.1700
Data Index: 3706598 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.0993. Min Act: -0.1700
Data Index: 2961469 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.0993. Min Act: -0.1700
Data Index: 6801570 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.0993. Min Act: -0.1700
Data Index: 5586295 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8806. Min Range: -4.8806
Max Act: 4.0993. Min Act: -0.1700
Data Index: 6624407 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19