Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2522 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.2806. Min Act: -0.1700
Data Index: 3093070 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.2181. Min Act: -0.1700
Data Index: 5030893 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.2181. Min Act: -0.1700
Data Index: 3912751 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.2181. Min Act: -0.1700
Data Index: 2062266 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.1868. Min Act: -0.1700
Data Index: 42609 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.1868. Min Act: -0.1700
Data Index: 8291526 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.1556. Min Act: -0.1699
Data Index: 4899422 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.1556. Min Act: -0.1700
Data Index: 6907991 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.1556. Min Act: -0.1700
Data Index: 6362779 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.1556. Min Act: -0.1700
Data Index: 2518420 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.1556. Min Act: -0.1699
Data Index: 5198522 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.0931. Min Act: -0.1700
Data Index: 6779059 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.1243. Min Act: -0.1700
Data Index: 6062253 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.1556. Min Act: -0.1700
Data Index: 2936776 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.0931. Min Act: -0.1700
Data Index: 5662236 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.0931. Min Act: -0.1700
Data Index: 1055268 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.0931. Min Act: -0.1700
Data Index: 8450441 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.0931. Min Act: -0.1699
Data Index: 3814955 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.0931. Min Act: -0.1700
Data Index: 2815626 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2806. Min Range: -4.2806
Max Act: 4.0618. Min Act: -0.1698
Data Index: 856029 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19