Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4866 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.8466. Min Act: -0.1700
Data Index: 4953085 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.7216. Min Act: -0.1700
Data Index: 3043827 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.6903. Min Act: -0.1700
Data Index: 5789753 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.6903. Min Act: -0.1700
Data Index: 8145997 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.6591. Min Act: -0.1700
Data Index: 8643203 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.6591. Min Act: -0.1700
Data Index: 4465921 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.6903. Min Act: -0.1700
Data Index: 738987 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.6278. Min Act: -0.1700
Data Index: 5023663 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.5966. Min Act: -0.1700
Data Index: 1417080 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.5966. Min Act: -0.1700
Data Index: 7429435 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.6278. Min Act: -0.1700
Data Index: 6104679 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.6278. Min Act: -0.1700
Data Index: 482290 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.5966. Min Act: -0.1700
Data Index: 3972813 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.5966. Min Act: -0.1700
Data Index: 5865154 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.5966. Min Act: -0.1700
Data Index: 2032569 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.5966. Min Act: -0.1700
Data Index: 5199106 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.5966. Min Act: -0.1700
Data Index: 3437006 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.5966. Min Act: -0.1700
Data Index: 8173946 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.5966. Min Act: -0.1700
Data Index: 3946456 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8466. Min Range: -5.8466
Max Act: 5.5966. Min Act: -0.1700
Data Index: 3414317 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19