Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4093 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.8848. Min Act: -0.1700
Data Index: 3531353 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.8066. Min Act: -0.1700
Data Index: 3924461 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.8066. Min Act: -0.1700
Data Index: 1683415 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.7753. Min Act: -0.1700
Data Index: 1700207 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.7753. Min Act: -0.1700
Data Index: 3051497 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.6971. Min Act: -0.1700
Data Index: 5219304 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.6971. Min Act: -0.1700
Data Index: 5314543 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.6971. Min Act: -0.1700
Data Index: 939519 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.6658. Min Act: -0.1700
Data Index: 2950498 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.6502. Min Act: -0.1700
Data Index: 8653466 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.6345. Min Act: -0.1700
Data Index: 5926885 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.6502. Min Act: -0.1700
Data Index: 5687762 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.6502. Min Act: -0.1700
Data Index: 7413266 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.6502. Min Act: -0.1700
Data Index: 4819789 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.6189. Min Act: -0.1700
Data Index: 4300253 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.6189. Min Act: -0.1700
Data Index: 8045895 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.6032. Min Act: -0.1700
Data Index: 4631690 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.6032. Min Act: -0.1700
Data Index: 808931 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.6032. Min Act: -0.1700
Data Index: 2527281 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8848. Min Range: -3.8848
Max Act: 3.6032. Min Act: -0.1700
Data Index: 616095 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19