Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4637 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.9000. Min Act: -0.1700
Data Index: 5794931 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.7125. Min Act: -0.1700
Data Index: 6229361 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.6813. Min Act: -0.1700
Data Index: 7046925 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.6500. Min Act: -0.1700
Data Index: 5030815 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.5875. Min Act: -0.1700
Data Index: 827319 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.4938. Min Act: -0.1700
Data Index: 7521645 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.4938. Min Act: -0.1700
Data Index: 6502356 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.4938. Min Act: -0.1700
Data Index: 6522075 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.5250. Min Act: -0.1700
Data Index: 7503318 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.4625. Min Act: -0.1700
Data Index: 7616778 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.4313. Min Act: -0.1700
Data Index: 3444210 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.4000. Min Act: -0.1700
Data Index: 8351280 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.3688. Min Act: -0.1700
Data Index: 8555244 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.3375. Min Act: -0.1700
Data Index: 6270505 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.3063. Min Act: -0.1700
Data Index: 4706715 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.2750. Min Act: -0.1700
Data Index: 2368224 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.2750. Min Act: -0.1700
Data Index: 6704462 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.3063. Min Act: -0.1700
Data Index: 583887 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.2750. Min Act: -0.1700
Data Index: 8300068 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9000. Min Range: -7.9000
Max Act: 7.2438. Min Act: -0.1700
Data Index: 7003277 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19