Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2600 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.9304. Min Act: -0.1700
Data Index: 3625998 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.8679. Min Act: -0.1700
Data Index: 3863394 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.8054. Min Act: -0.1700
Data Index: 8429032 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.7742. Min Act: -0.1700
Data Index: 3175429 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.7742. Min Act: -0.1700
Data Index: 6429305 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.7429. Min Act: -0.1700
Data Index: 2560691 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.7117. Min Act: -0.1700
Data Index: 8217372 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.7117. Min Act: -0.1700
Data Index: 8070037 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.7117. Min Act: -0.1700
Data Index: 4341143 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.7117. Min Act: -0.1700
Data Index: 5779083 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.6804. Min Act: -0.1700
Data Index: 6863798 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.6804. Min Act: -0.1700
Data Index: 365395 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.6492. Min Act: -0.1700
Data Index: 7797809 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.6492. Min Act: -0.1700
Data Index: 8169654 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.6179. Min Act: -0.1700
Data Index: 4354379 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.5867. Min Act: -0.1700
Data Index: 8042526 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.5867. Min Act: -0.1700
Data Index: 8263577 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.5867. Min Act: -0.1700
Data Index: 2897983 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.5867. Min Act: -0.1700
Data Index: 5558594 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9304. Min Range: -5.9304
Max Act: 5.5867. Min Act: -0.1700
Data Index: 5269288 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19