Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3722 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.2170. Min Act: -0.1700
Data Index: 6378018 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.2170. Min Act: -0.1700
Data Index: 316297 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1857. Min Act: -0.1700
Data Index: 8196221 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1857. Min Act: -0.1700
Data Index: 2209927 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1857. Min Act: -0.1700
Data Index: 2866364 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1545. Min Act: -0.1700
Data Index: 1859995 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1545. Min Act: -0.1700
Data Index: 6484043 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1545. Min Act: -0.1700
Data Index: 3414704 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1545. Min Act: -0.1700
Data Index: 3428839 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1545. Min Act: -0.1700
Data Index: 2113609 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1545. Min Act: -0.1700
Data Index: 834564 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1545. Min Act: -0.1700
Data Index: 7229729 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1545. Min Act: -0.1700
Data Index: 7477095 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1232. Min Act: -0.1700
Data Index: 5457336 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1232. Min Act: -0.1700
Data Index: 1691878 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1232. Min Act: -0.1700
Data Index: 3075533 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1232. Min Act: -0.1700
Data Index: 3799293 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1232. Min Act: -0.1700
Data Index: 1169058 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1232. Min Act: -0.1700
Data Index: 536733 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1232. Min Act: -0.1700
Data Index: 7664365 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19