Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 615 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2043. Min Range: -7.2043
Max Act: 7.2043. Min Act: -0.1700
Data Index: 7859001 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2043. Min Range: -7.2043
Max Act: 7.2043. Min Act: -0.1700
Data Index: 33574 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2043. Min Range: -7.2043
Max Act: 7.1418. Min Act: -0.1700
Data Index: 1588850 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2043. Min Range: -7.2043
Max Act: 7.0793. Min Act: -0.1700
Data Index: 6475211 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2043. Min Range: -7.2043
Max Act: 7.0793. Min Act: -0.1700
Data Index: 6332399 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2043. Min Range: -7.2043
Max Act: 6.9856. Min Act: -0.1700
Data Index: 7241661 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2043. Min Range: -7.2043
Max Act: 6.9231. Min Act: -0.1700
Data Index: 8248474 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2043. Min Range: -7.2043
Max Act: 6.8606. Min Act: -0.1700
Data Index: 1401827 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2043. Min Range: -7.2043
Max Act: 6.8606. Min Act: -0.1700
Data Index: 7609227 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2043. Min Range: -7.2043
Max Act: 6.8606. Min Act: -0.1700
Data Index: 8327179 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2043. Min Range: -7.2043
Max Act: 6.8293. Min Act: -0.1700
Data Index: 4107058 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2043. Min Range: -7.2043
Max Act: 6.8293. Min Act: -0.1700
Data Index: 8081766 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2043. Min Range: -7.2043
Max Act: 6.7981. Min Act: -0.1700
Data Index: 622178 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2043. Min Range: -7.2043
Max Act: 6.7981. Min Act: -0.1700
Data Index: 5421769 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2043. Min Range: -7.2043
Max Act: 6.7981. Min Act: -0.1700
Data Index: 6530667 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2043. Min Range: -7.2043
Max Act: 6.7981. Min Act: -0.1700
Data Index: 7130328 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2043. Min Range: -7.2043
Max Act: 6.7668. Min Act: -0.1700
Data Index: 1128006 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2043. Min Range: -7.2043
Max Act: 6.7668. Min Act: -0.1700
Data Index: 8157044 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2043. Min Range: -7.2043
Max Act: 6.7668. Min Act: -0.1700
Data Index: 8716185 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2043. Min Range: -7.2043
Max Act: 6.7668. Min Act: -0.1700
Data Index: 172501 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19