Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3553 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.1917. Min Act: -0.1700
Data Index: 5351732 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.1604. Min Act: -0.1700
Data Index: 6956939 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.1604. Min Act: -0.1700
Data Index: 393462 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.1604. Min Act: -0.1700
Data Index: 4500729 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.1604. Min Act: -0.1700
Data Index: 5542554 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.1604. Min Act: -0.1700
Data Index: 3491521 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.1292. Min Act: -0.1700
Data Index: 757930 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.1292. Min Act: -0.1700
Data Index: 6775138 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.1292. Min Act: -0.1700
Data Index: 8360964 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.1292. Min Act: -0.1700
Data Index: 7446339 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.1292. Min Act: -0.1700
Data Index: 3162403 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.0979. Min Act: -0.1700
Data Index: 1244823 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.0979. Min Act: -0.1700
Data Index: 8360973 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.0979. Min Act: -0.1700
Data Index: 7291471 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.0979. Min Act: -0.1700
Data Index: 7040101 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.0979. Min Act: -0.1700
Data Index: 7006654 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.0979. Min Act: -0.1700
Data Index: 73341 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.0667. Min Act: -0.1700
Data Index: 6004386 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.0667. Min Act: -0.1700
Data Index: 5550438 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1917. Min Range: -4.1917
Max Act: 4.0979. Min Act: -0.1700
Data Index: 2001033 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19