Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1899 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.9234. Min Act: -0.1700
Data Index: 7908783 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.8609. Min Act: -0.1700
Data Index: 6985534 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.7672. Min Act: -0.1700
Data Index: 880266 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.5484. Min Act: -0.1700
Data Index: 1965584 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.5172. Min Act: -0.1700
Data Index: 2932441 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.4547. Min Act: -0.1700
Data Index: 5230339 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.4547. Min Act: -0.1700
Data Index: 5007993 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.4234. Min Act: -0.1700
Data Index: 593688 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.4234. Min Act: -0.1700
Data Index: 5408516 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.3922. Min Act: -0.1700
Data Index: 8540003 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.3922. Min Act: -0.1700
Data Index: 6354473 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.3922. Min Act: -0.1700
Data Index: 7340405 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.3922. Min Act: -0.1700
Data Index: 8227617 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.3922. Min Act: -0.1700
Data Index: 1486580 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.3609. Min Act: -0.1700
Data Index: 3127339 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.3609. Min Act: -0.1700
Data Index: 7595097 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.3609. Min Act: -0.1700
Data Index: 4040034 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.3297. Min Act: -0.1700
Data Index: 7923997 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.3297. Min Act: -0.1700
Data Index: 1138483 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9234. Min Range: -6.9234
Max Act: 6.3609. Min Act: -0.1700
Data Index: 7779223 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19