Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1444 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2533. Min Act: -0.0001

Data Index: 675643 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2517. Min Act: -0.0001

Data Index: 833847 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2457. Min Act: -0.0000

Data Index: 304698 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2355. Min Act: -0.0001

Data Index: 242683 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2360. Min Act: -0.0001

Data Index: 635816 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2273. Min Act: -0.0000

Data Index: 32721 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2328. Min Act: -0.0000

Data Index: 136553 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2268. Min Act: -0.0001

Data Index: 1064958 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2283. Min Act: -0.0000

Data Index: 877136 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1079320 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2228. Min Act: -0.0001

Data Index: 135277 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2192. Min Act: -0.0001

Data Index: 432447 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2135. Min Act: -0.0000

Data Index: 416744 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2062. Min Act: -0.0001

Data Index: 835841 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2118. Min Act: -0.0001

Data Index: 123127 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2108. Min Act: -0.0000

Data Index: 486327 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2095. Min Act: -0.0000

Data Index: 367608 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2091. Min Act: -0.0001

Data Index: 1219662 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2083. Min Act: -0.0001

Data Index: 780267 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.2533. Min Range: -0.2533

Max Act: 0.2063. Min Act: -0.0001

Data Index: 580192 (C4 (Web Text))

Max Activating Token Index: 398