Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 420 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.8636. Min Act: -0.1700
Data Index: 4351898 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.8323. Min Act: -0.1700
Data Index: 8070014 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.8011. Min Act: -0.1700
Data Index: 7538077 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.7386. Min Act: -0.1700
Data Index: 2909869 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.7073. Min Act: -0.1700
Data Index: 4513700 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.7073. Min Act: -0.1700
Data Index: 413748 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.6761. Min Act: -0.1700
Data Index: 2300195 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.6761. Min Act: -0.1700
Data Index: 3830646 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.6761. Min Act: -0.1700
Data Index: 2909188 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.6448. Min Act: -0.1700
Data Index: 44298 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.6448. Min Act: -0.1700
Data Index: 4368066 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.6448. Min Act: -0.1700
Data Index: 4814914 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.6136. Min Act: -0.1700
Data Index: 4409829 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.6448. Min Act: -0.1699
Data Index: 8194170 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.5823. Min Act: -0.1700
Data Index: 144504 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.5823. Min Act: -0.1700
Data Index: 1798338 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.5511. Min Act: -0.1700
Data Index: 4962010 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.5823. Min Act: -0.1700
Data Index: 5965645 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.5198. Min Act: -0.1700
Data Index: 513753 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.5198. Min Act: -0.1700
Data Index: 3275910 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19