Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.5829. Min Act: -0.1700
Data Index: 8825512 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.5517. Min Act: -0.1700
Data Index: 3542931 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.5204. Min Act: -0.1700
Data Index: 2065530 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.5517. Min Act: -0.1700
Data Index: 6213573 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.5204. Min Act: -0.1700
Data Index: 3278510 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.5517. Min Act: -0.1700
Data Index: 6128622 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.5204. Min Act: -0.1700
Data Index: 8465001 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.4892. Min Act: -0.1700
Data Index: 8116272 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.4892. Min Act: -0.1700
Data Index: 4713747 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.4892. Min Act: -0.1700
Data Index: 7617649 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.4579. Min Act: -0.1700
Data Index: 1397552 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.4579. Min Act: -0.1700
Data Index: 8090844 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.4579. Min Act: -0.1700
Data Index: 5712583 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.4579. Min Act: -0.1700
Data Index: 1850605 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.4267. Min Act: -0.1700
Data Index: 90128 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.4267. Min Act: -0.1700
Data Index: 4690236 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.4267. Min Act: -0.1700
Data Index: 481931 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.4267. Min Act: -0.1700
Data Index: 233164 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.4267. Min Act: -0.1700
Data Index: 1528419 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5829. Min Range: -5.5829
Max Act: 5.4267. Min Act: -0.1700
Data Index: 8037337 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19