Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.4009. Min Act: -0.1700
Data Index: 4222444 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.3072. Min Act: -0.1700
Data Index: 4230246 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.1821. Min Act: -0.1700
Data Index: 1425807 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.1821. Min Act: -0.1700
Data Index: 8197451 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.1821. Min Act: -0.1700
Data Index: 62299 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.1821. Min Act: -0.1700
Data Index: 8098624 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.1821. Min Act: -0.1700
Data Index: 6635268 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.1821. Min Act: -0.1700
Data Index: 6296115 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.1821. Min Act: -0.1700
Data Index: 14432 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.1821. Min Act: -0.1700
Data Index: 5578631 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.1821. Min Act: -0.1700
Data Index: 2880935 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.1821. Min Act: -0.1700
Data Index: 2685434 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.1821. Min Act: -0.1700
Data Index: 4765593 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.1821. Min Act: -0.1700
Data Index: 175368 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.1196. Min Act: -0.1700
Data Index: 3603465 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.1509. Min Act: -0.1700
Data Index: 7173220 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.0884. Min Act: -0.1700
Data Index: 1722583 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.1509. Min Act: -0.1700
Data Index: 1663083 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.1509. Min Act: -0.1700
Data Index: 7821893 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4009. Min Range: -4.4009
Max Act: 4.1196. Min Act: -0.1700
Data Index: 7066088 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19