Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1675 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.7911. Min Act: -0.1700
Data Index: 4283840 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.6953. Min Act: -0.1700
Data Index: 8618795 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.6793. Min Act: -0.1700
Data Index: 6835552 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.6472. Min Act: -0.1700
Data Index: 6835555 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.6312. Min Act: -0.1700
Data Index: 7309205 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.6151. Min Act: -0.1700
Data Index: 882947 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.6312. Min Act: -0.1700
Data Index: 1534617 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.5829. Min Act: -0.1700
Data Index: 6835558 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.5829. Min Act: -0.1700
Data Index: 1160257 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.5990. Min Act: -0.1700
Data Index: 6835553 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.5829. Min Act: -0.1700
Data Index: 6835554 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.5668. Min Act: -0.1700
Data Index: 7839880 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.5506. Min Act: -0.1700
Data Index: 3567586 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.5345. Min Act: -0.1700
Data Index: 6058739 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.5345. Min Act: -0.1700
Data Index: 6835556 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.5345. Min Act: -0.1700
Data Index: 773420 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.5345. Min Act: -0.1700
Data Index: 8634703 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.5345. Min Act: -0.1700
Data Index: 5850390 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.5345. Min Act: -0.1700
Data Index: 2978034 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7911. Min Range: -2.7911
Max Act: 2.5183. Min Act: -0.1700
Data Index: 4556261 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19