Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3734 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4687. Min Act: -0.1700
Data Index: 1657867 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4687. Min Act: -0.1700
Data Index: 5143645 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4687. Min Act: -0.1700
Data Index: 5143626 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4687. Min Act: -0.1700
Data Index: 5143628 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4863. Min Act: -0.1700
Data Index: 2427900 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4687. Min Act: -0.1700
Data Index: 5143640 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4687. Min Act: -0.1700
Data Index: 8606345 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4863. Min Act: -0.1700
Data Index: 6214374 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4687. Min Act: -0.1700
Data Index: 5143641 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4687. Min Act: -0.1699
Data Index: 5143639 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4687. Min Act: -0.1700
Data Index: 5143646 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4687. Min Act: -0.1700
Data Index: 5143649 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4511. Min Act: -0.1700
Data Index: 5143631 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4511. Min Act: -0.1700
Data Index: 5143627 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4511. Min Act: -0.1699
Data Index: 5143637 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4511. Min Act: -0.1700
Data Index: 5143633 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4511. Min Act: -0.1700
Data Index: 5143642 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4511. Min Act: -0.1700
Data Index: 5143643 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4511. Min Act: -0.1700
Data Index: 5143632 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4863. Min Range: -1.4863
Max Act: 1.4687. Min Act: -0.1700
Data Index: 5143644 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19