Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 564 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2039. Min Range: -3.2039
Max Act: 3.2039. Min Act: -0.1700
Data Index: 1349886 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2039. Min Range: -3.2039
Max Act: 3.1724. Min Act: -0.1700
Data Index: 3141346 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2039. Min Range: -3.2039
Max Act: 3.1252. Min Act: -0.1700
Data Index: 2689459 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2039. Min Range: -3.2039
Max Act: 3.1252. Min Act: -0.1700
Data Index: 8362530 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2039. Min Range: -3.2039
Max Act: 3.1567. Min Act: -0.1700
Data Index: 936687 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2039. Min Range: -3.2039
Max Act: 3.0779. Min Act: -0.1700
Data Index: 3026052 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2039. Min Range: -3.2039
Max Act: 3.0937. Min Act: -0.1700
Data Index: 5010016 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2039. Min Range: -3.2039
Max Act: 3.0621. Min Act: -0.1700
Data Index: 3763338 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2039. Min Range: -3.2039
Max Act: 3.0779. Min Act: -0.1700
Data Index: 4955653 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2039. Min Range: -3.2039
Max Act: 3.0621. Min Act: -0.1700
Data Index: 7768220 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2039. Min Range: -3.2039
Max Act: 3.0779. Min Act: -0.1700
Data Index: 8329064 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2039. Min Range: -3.2039
Max Act: 3.0621. Min Act: -0.1700
Data Index: 1576270 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2039. Min Range: -3.2039
Max Act: 3.0621. Min Act: -0.1700
Data Index: 693996 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2039. Min Range: -3.2039
Max Act: 3.0148. Min Act: -0.1700
Data Index: 1790754 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2039. Min Range: -3.2039
Max Act: 3.0464. Min Act: -0.1700
Data Index: 6648197 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2039. Min Range: -3.2039
Max Act: 3.0306. Min Act: -0.1700
Data Index: 8486507 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2039. Min Range: -3.2039
Max Act: 3.0464. Min Act: -0.1700
Data Index: 964313 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2039. Min Range: -3.2039
Max Act: 2.9990. Min Act: -0.1700
Data Index: 1789681 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2039. Min Range: -3.2039
Max Act: 3.0306. Min Act: -0.1700
Data Index: 3182602 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2039. Min Range: -3.2039
Max Act: 3.0148. Min Act: -0.1700
Data Index: 7375540 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19