Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2624 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.5499. Min Act: -0.1700
Data Index: 6046484 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.5849. Min Act: -0.1700
Data Index: 7227448 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.5148. Min Act: -0.1700
Data Index: 543077 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.5148. Min Act: -0.1700
Data Index: 8527589 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.4973. Min Act: -0.1700
Data Index: 755453 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.4973. Min Act: -0.1700
Data Index: 3053225 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.4973. Min Act: -0.1700
Data Index: 7911850 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.4797. Min Act: -0.1700
Data Index: 3681319 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.4797. Min Act: -0.1700
Data Index: 2225007 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.4797. Min Act: -0.1700
Data Index: 7397212 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.4621. Min Act: -0.1700
Data Index: 8411826 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.4621. Min Act: -0.1700
Data Index: 4126246 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.4621. Min Act: -0.1700
Data Index: 1313638 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.4621. Min Act: -0.1700
Data Index: 1472647 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.4621. Min Act: -0.1700
Data Index: 2689230 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.4445. Min Act: -0.1700
Data Index: 7462537 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.4445. Min Act: -0.1700
Data Index: 6700400 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.4445. Min Act: -0.1700
Data Index: 5964690 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.4269. Min Act: -0.1700
Data Index: 1000276 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5849. Min Range: -1.5849
Max Act: 1.4269. Min Act: -0.1700
Data Index: 38668 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19