Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3020 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.9563. Min Act: -0.1700
Data Index: 7066910 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.9250. Min Act: -0.1700
Data Index: 4041755 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.8938. Min Act: -0.1700
Data Index: 6640113 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.8938. Min Act: -0.1700
Data Index: 7360254 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.8313. Min Act: -0.1700
Data Index: 549910 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.7688. Min Act: -0.1700
Data Index: 312767 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.8625. Min Act: -0.1700
Data Index: 4175295 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.6750. Min Act: -0.1700
Data Index: 3344346 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.7375. Min Act: -0.1700
Data Index: 884667 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.8000. Min Act: -0.1700
Data Index: 1634226 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.7688. Min Act: -0.1700
Data Index: 2557751 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.8313. Min Act: -0.1700
Data Index: 5659978 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.7063. Min Act: -0.1700
Data Index: 7156972 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.7375. Min Act: -0.1700
Data Index: 7596429 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.7375. Min Act: -0.1700
Data Index: 1582282 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.6750. Min Act: -0.1700
Data Index: 2343883 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.6750. Min Act: -0.1700
Data Index: 8555964 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.6750. Min Act: -0.1700
Data Index: 3766164 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.6750. Min Act: -0.1700
Data Index: 5666130 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9563. Min Range: -4.9563
Max Act: 4.6438. Min Act: -0.1700
Data Index: 125497 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19