Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5380 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5209. Min Range: -8.5209
Max Act: 8.5209. Min Act: -0.1700
Data Index: 1224102 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5209. Min Range: -8.5209
Max Act: 8.4584. Min Act: -0.1700
Data Index: 3247230 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5209. Min Range: -8.5209
Max Act: 8.3334. Min Act: -0.1700
Data Index: 3987727 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5209. Min Range: -8.5209
Max Act: 8.0834. Min Act: -0.1700
Data Index: 7423570 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5209. Min Range: -8.5209
Max Act: 8.0209. Min Act: -0.1700
Data Index: 5814542 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5209. Min Range: -8.5209
Max Act: 7.9584. Min Act: -0.1700
Data Index: 6323713 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5209. Min Range: -8.5209
Max Act: 7.9584. Min Act: -0.1700
Data Index: 1641159 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5209. Min Range: -8.5209
Max Act: 7.9584. Min Act: -0.1700
Data Index: 2104951 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5209. Min Range: -8.5209
Max Act: 7.9584. Min Act: -0.1700
Data Index: 5530467 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5209. Min Range: -8.5209
Max Act: 8.0209. Min Act: -0.1700
Data Index: 8464953 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5209. Min Range: -8.5209
Max Act: 7.8334. Min Act: -0.1700
Data Index: 2303071 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5209. Min Range: -8.5209
Max Act: 7.7709. Min Act: -0.1700
Data Index: 5084078 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5209. Min Range: -8.5209
Max Act: 7.8334. Min Act: -0.1700
Data Index: 1598487 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5209. Min Range: -8.5209
Max Act: 7.7709. Min Act: -0.1700
Data Index: 199060 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5209. Min Range: -8.5209
Max Act: 7.7084. Min Act: -0.1700
Data Index: 7282719 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5209. Min Range: -8.5209
Max Act: 7.7709. Min Act: -0.1700
Data Index: 2796939 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5209. Min Range: -8.5209
Max Act: 7.7709. Min Act: -0.1700
Data Index: 5952722 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5209. Min Range: -8.5209
Max Act: 7.7084. Min Act: -0.1700
Data Index: 7115439 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5209. Min Range: -8.5209
Max Act: 7.7084. Min Act: -0.1700
Data Index: 3886840 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5209. Min Range: -8.5209
Max Act: 7.7084. Min Act: -0.1700
Data Index: 4717420 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19