Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2113 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4727. Min Range: -4.4727
Max Act: 4.4727. Min Act: -0.1700
Data Index: 1371451 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4727. Min Range: -4.4727
Max Act: 4.4102. Min Act: -0.1700
Data Index: 6124031 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4727. Min Range: -4.4727
Max Act: 4.3789. Min Act: -0.1700
Data Index: 7520988 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4727. Min Range: -4.4727
Max Act: 4.2852. Min Act: -0.1700
Data Index: 6740727 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4727. Min Range: -4.4727
Max Act: 4.2539. Min Act: -0.1700
Data Index: 274517 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4727. Min Range: -4.4727
Max Act: 4.2227. Min Act: -0.1700
Data Index: 891414 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4727. Min Range: -4.4727
Max Act: 4.1914. Min Act: -0.1700
Data Index: 2970749 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4727. Min Range: -4.4727
Max Act: 4.2227. Min Act: -0.1700
Data Index: 1381634 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4727. Min Range: -4.4727
Max Act: 4.1289. Min Act: -0.1700
Data Index: 4114249 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4727. Min Range: -4.4727
Max Act: 4.1289. Min Act: -0.1700
Data Index: 707516 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4727. Min Range: -4.4727
Max Act: 4.0976. Min Act: -0.1700
Data Index: 1955439 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4727. Min Range: -4.4727
Max Act: 4.0664. Min Act: -0.1700
Data Index: 2782443 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4727. Min Range: -4.4727
Max Act: 4.0664. Min Act: -0.1700
Data Index: 4128517 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4727. Min Range: -4.4727
Max Act: 4.0351. Min Act: -0.1700
Data Index: 1597835 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4727. Min Range: -4.4727
Max Act: 4.0039. Min Act: -0.1700
Data Index: 6210683 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4727. Min Range: -4.4727
Max Act: 4.0039. Min Act: -0.1700
Data Index: 2833629 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4727. Min Range: -4.4727
Max Act: 4.0039. Min Act: -0.1700
Data Index: 1347583 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4727. Min Range: -4.4727
Max Act: 4.0039. Min Act: -0.1700
Data Index: 6594490 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4727. Min Range: -4.4727
Max Act: 3.9726. Min Act: -0.1700
Data Index: 850962 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4727. Min Range: -4.4727
Max Act: 3.9413. Min Act: -0.1700
Data Index: 6542333 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19