Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 516 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.3981. Min Act: -0.1700
Data Index: 8375783 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.3668. Min Act: -0.1700
Data Index: 7135962 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.3043. Min Act: -0.1700
Data Index: 7525973 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.2731. Min Act: -0.1700
Data Index: 5429482 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.2418. Min Act: -0.1700
Data Index: 5786054 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.1793. Min Act: -0.1700
Data Index: 5463689 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.1481. Min Act: -0.1700
Data Index: 3444439 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.1168. Min Act: -0.1700
Data Index: 4899649 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.1168. Min Act: -0.1700
Data Index: 4939636 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.1168. Min Act: -0.1700
Data Index: 7752855 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.0856. Min Act: -0.1700
Data Index: 4298761 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.0856. Min Act: -0.1700
Data Index: 2610655 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.0856. Min Act: -0.1700
Data Index: 784640 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.0856. Min Act: -0.1700
Data Index: 208777 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.0856. Min Act: -0.1700
Data Index: 6619721 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.0856. Min Act: -0.1700
Data Index: 71467 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.0543. Min Act: -0.1700
Data Index: 8180392 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.0543. Min Act: -0.1700
Data Index: 3359930 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.0543. Min Act: -0.1700
Data Index: 2551013 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3981. Min Range: -5.3981
Max Act: 4.9918. Min Act: -0.1700
Data Index: 7583334 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19