Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 75 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2727. Min Range: -7.2727
Max Act: 7.2727. Min Act: -0.1700
Data Index: 6156893 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2727. Min Range: -7.2727
Max Act: 7.1790. Min Act: -0.1700
Data Index: 1964194 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2727. Min Range: -7.2727
Max Act: 7.0540. Min Act: -0.1700
Data Index: 8636203 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2727. Min Range: -7.2727
Max Act: 7.0540. Min Act: -0.1700
Data Index: 3752961 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2727. Min Range: -7.2727
Max Act: 6.9602. Min Act: -0.1700
Data Index: 2379654 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2727. Min Range: -7.2727
Max Act: 6.9915. Min Act: -0.1700
Data Index: 5569099 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2727. Min Range: -7.2727
Max Act: 6.9602. Min Act: -0.1700
Data Index: 5030769 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2727. Min Range: -7.2727
Max Act: 6.9602. Min Act: -0.1700
Data Index: 6912696 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2727. Min Range: -7.2727
Max Act: 6.8977. Min Act: -0.1700
Data Index: 5247289 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2727. Min Range: -7.2727
Max Act: 6.9290. Min Act: -0.1700
Data Index: 5260910 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2727. Min Range: -7.2727
Max Act: 6.8977. Min Act: -0.1700
Data Index: 3274032 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2727. Min Range: -7.2727
Max Act: 6.8352. Min Act: -0.1700
Data Index: 1660467 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2727. Min Range: -7.2727
Max Act: 6.8977. Min Act: -0.1700
Data Index: 6546496 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2727. Min Range: -7.2727
Max Act: 6.8665. Min Act: -0.1700
Data Index: 7756743 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2727. Min Range: -7.2727
Max Act: 6.8040. Min Act: -0.1700
Data Index: 8718514 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2727. Min Range: -7.2727
Max Act: 6.8040. Min Act: -0.1700
Data Index: 260188 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2727. Min Range: -7.2727
Max Act: 6.7415. Min Act: -0.1700
Data Index: 4113792 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2727. Min Range: -7.2727
Max Act: 6.7415. Min Act: -0.1700
Data Index: 2716842 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2727. Min Range: -7.2727
Max Act: 6.7727. Min Act: -0.1700
Data Index: 2874384 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2727. Min Range: -7.2727
Max Act: 6.7727. Min Act: -0.1700
Data Index: 3706229 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19