Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1025 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6718. Min Act: -0.1700
Data Index: 1843063 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6405. Min Act: -0.1700
Data Index: 1741939 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6249. Min Act: -0.1700
Data Index: 2655038 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6405. Min Act: -0.1700
Data Index: 207959 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6405. Min Act: -0.1700
Data Index: 513185 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.6092. Min Act: -0.1700
Data Index: 5740298 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.5936. Min Act: -0.1700
Data Index: 656705 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.5623. Min Act: -0.1700
Data Index: 8636593 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.5779. Min Act: -0.1700
Data Index: 7500217 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.5623. Min Act: -0.1700
Data Index: 7600491 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.5466. Min Act: -0.1700
Data Index: 215813 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.5466. Min Act: -0.1700
Data Index: 2482552 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.5466. Min Act: -0.1700
Data Index: 585998 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.5310. Min Act: -0.1700
Data Index: 1962195 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.5310. Min Act: -0.1700
Data Index: 7384674 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.5153. Min Act: -0.1700
Data Index: 7962872 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.4996. Min Act: -0.1700
Data Index: 4097368 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.5310. Min Act: -0.1700
Data Index: 5951682 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.4996. Min Act: -0.1700
Data Index: 4148030 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6718. Min Range: -3.6718
Max Act: 3.5153. Min Act: -0.1700
Data Index: 4322198 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19