Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3558 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7386. Min Range: -8.7386
Max Act: 8.7386. Min Act: -0.1700
Data Index: 8020461 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7386. Min Range: -8.7386
Max Act: 8.4886. Min Act: -0.1700
Data Index: 8529439 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7386. Min Range: -8.7386
Max Act: 8.4886. Min Act: -0.1700
Data Index: 6593529 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7386. Min Range: -8.7386
Max Act: 8.3011. Min Act: -0.1700
Data Index: 3805994 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7386. Min Range: -8.7386
Max Act: 8.3011. Min Act: -0.1700
Data Index: 4202918 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7386. Min Range: -8.7386
Max Act: 8.2386. Min Act: -0.1700
Data Index: 8419992 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7386. Min Range: -8.7386
Max Act: 8.1761. Min Act: -0.1700
Data Index: 11745 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7386. Min Range: -8.7386
Max Act: 8.1761. Min Act: -0.1700
Data Index: 2370616 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7386. Min Range: -8.7386
Max Act: 8.1761. Min Act: -0.1700
Data Index: 7192222 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7386. Min Range: -8.7386
Max Act: 8.1761. Min Act: -0.1700
Data Index: 4833920 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7386. Min Range: -8.7386
Max Act: 8.1761. Min Act: -0.1700
Data Index: 4079312 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7386. Min Range: -8.7386
Max Act: 8.1136. Min Act: -0.1700
Data Index: 6846094 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7386. Min Range: -8.7386
Max Act: 8.1136. Min Act: -0.1700
Data Index: 3116322 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7386. Min Range: -8.7386
Max Act: 8.0511. Min Act: -0.1700
Data Index: 5057895 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7386. Min Range: -8.7386
Max Act: 8.1136. Min Act: -0.1700
Data Index: 5937833 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7386. Min Range: -8.7386
Max Act: 8.0511. Min Act: -0.1700
Data Index: 765286 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7386. Min Range: -8.7386
Max Act: 8.0511. Min Act: -0.1700
Data Index: 1308848 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7386. Min Range: -8.7386
Max Act: 8.0511. Min Act: -0.1700
Data Index: 8709404 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7386. Min Range: -8.7386
Max Act: 7.9886. Min Act: -0.1700
Data Index: 6914091 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7386. Min Range: -8.7386
Max Act: 7.9261. Min Act: -0.1700
Data Index: 7502723 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19