Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1233 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4051. Min Range: -6.4051
Max Act: 6.4051. Min Act: -0.1700
Data Index: 6116261 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4051. Min Range: -6.4051
Max Act: 6.3113. Min Act: -0.1700
Data Index: 8774325 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4051. Min Range: -6.4051
Max Act: 6.1551. Min Act: -0.1700
Data Index: 4455391 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4051. Min Range: -6.4051
Max Act: 6.1238. Min Act: -0.1700
Data Index: 3024700 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4051. Min Range: -6.4051
Max Act: 6.0926. Min Act: -0.1700
Data Index: 7694070 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4051. Min Range: -6.4051
Max Act: 6.0926. Min Act: -0.1700
Data Index: 799354 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4051. Min Range: -6.4051
Max Act: 6.0613. Min Act: -0.1700
Data Index: 7694068 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4051. Min Range: -6.4051
Max Act: 6.0613. Min Act: -0.1700
Data Index: 280417 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4051. Min Range: -6.4051
Max Act: 6.0301. Min Act: -0.1700
Data Index: 3024699 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4051. Min Range: -6.4051
Max Act: 5.9988. Min Act: -0.1700
Data Index: 2216792 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4051. Min Range: -6.4051
Max Act: 5.9988. Min Act: -0.1700
Data Index: 911076 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4051. Min Range: -6.4051
Max Act: 5.9363. Min Act: -0.1700
Data Index: 5477341 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4051. Min Range: -6.4051
Max Act: 5.9676. Min Act: -0.1700
Data Index: 4764570 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4051. Min Range: -6.4051
Max Act: 5.9363. Min Act: -0.1700
Data Index: 3110739 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4051. Min Range: -6.4051
Max Act: 5.9051. Min Act: -0.1700
Data Index: 374901 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4051. Min Range: -6.4051
Max Act: 5.8738. Min Act: -0.1700
Data Index: 121958 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4051. Min Range: -6.4051
Max Act: 5.8738. Min Act: -0.1700
Data Index: 6536683 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4051. Min Range: -6.4051
Max Act: 5.9051. Min Act: -0.1700
Data Index: 7459800 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4051. Min Range: -6.4051
Max Act: 5.8426. Min Act: -0.1700
Data Index: 2707197 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4051. Min Range: -6.4051
Max Act: 5.8426. Min Act: -0.1700
Data Index: 5510744 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19