Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3514 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.3511. Min Act: -0.1700
Data Index: 3891649 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.2573. Min Act: -0.1700
Data Index: 4146771 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.2261. Min Act: -0.1700
Data Index: 6307897 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.1948. Min Act: -0.1700
Data Index: 3762932 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.2261. Min Act: -0.1700
Data Index: 301747 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.1948. Min Act: -0.1700
Data Index: 6651774 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.1948. Min Act: -0.1700
Data Index: 1862639 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.1636. Min Act: -0.1700
Data Index: 6319387 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.1636. Min Act: -0.1700
Data Index: 3847677 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.1636. Min Act: -0.1700
Data Index: 5653793 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.1636. Min Act: -0.1700
Data Index: 1785165 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.1636. Min Act: -0.1700
Data Index: 7917200 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.1636. Min Act: -0.1700
Data Index: 4323412 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.1323. Min Act: -0.1700
Data Index: 1785164 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.1323. Min Act: -0.1700
Data Index: 4629024 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.1323. Min Act: -0.1700
Data Index: 3606599 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.1323. Min Act: -0.1700
Data Index: 468821 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.1323. Min Act: -0.1700
Data Index: 2464108 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.1323. Min Act: -0.1700
Data Index: 1644504 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3511. Min Range: -4.3511
Max Act: 4.1636. Min Act: -0.1700
Data Index: 1576521 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19