Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2678 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2299. Min Range: -4.2299
Max Act: 4.2299. Min Act: -0.1700
Data Index: 1253758 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2299. Min Range: -4.2299
Max Act: 4.0736. Min Act: -0.1700
Data Index: 3274584 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2299. Min Range: -4.2299
Max Act: 4.0736. Min Act: -0.1700
Data Index: 2631152 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2299. Min Range: -4.2299
Max Act: 4.0423. Min Act: -0.1700
Data Index: 2093063 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2299. Min Range: -4.2299
Max Act: 4.0111. Min Act: -0.1700
Data Index: 2558034 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2299. Min Range: -4.2299
Max Act: 4.0423. Min Act: -0.1700
Data Index: 5963869 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2299. Min Range: -4.2299
Max Act: 4.0111. Min Act: -0.1700
Data Index: 3328960 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2299. Min Range: -4.2299
Max Act: 4.0111. Min Act: -0.1700
Data Index: 3224617 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2299. Min Range: -4.2299
Max Act: 4.0111. Min Act: -0.1700
Data Index: 2425568 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2299. Min Range: -4.2299
Max Act: 4.0111. Min Act: -0.1700
Data Index: 4415680 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2299. Min Range: -4.2299
Max Act: 4.0111. Min Act: -0.1700
Data Index: 4671861 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.9798. Min Act: -0.1700
Data Index: 1037538 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.9485. Min Act: -0.1700
Data Index: 1454771 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.9485. Min Act: -0.1700
Data Index: 881984 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.9485. Min Act: -0.1700
Data Index: 426757 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.9485. Min Act: -0.1700
Data Index: 5310193 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.9173. Min Act: -0.1700
Data Index: 1322276 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.9173. Min Act: -0.1700
Data Index: 7762388 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.9173. Min Act: -0.1700
Data Index: 7448839 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.9173. Min Act: -0.1700
Data Index: 1094542 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19