Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1346 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2456. Min Act: -0.0000

Data Index: 672882 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2249. Min Act: -0.0000

Data Index: 354992 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2192. Min Act: -0.0000

Data Index: 764416 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2126. Min Act: -0.0000

Data Index: 727307 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1346006 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1093906 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1929. Min Act: -0.0000

Data Index: 133448 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1935. Min Act: -0.0000

Data Index: 150920 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1925. Min Act: -0.0000

Data Index: 74581 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1901. Min Act: -0.0000

Data Index: 726436 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1212834 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1713. Min Act: -0.0000

Data Index: 147985 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1885. Min Act: -0.0000

Data Index: 168801 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1817. Min Act: -0.0000

Data Index: 263667 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1873. Min Act: -0.0000

Data Index: 789233 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1558. Min Act: -0.0000

Data Index: 114251 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1610. Min Act: -0.0000

Data Index: 675493 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1805. Min Act: -0.0000

Data Index: 762380 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1716. Min Act: -0.0000

Data Index: 1292176 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1776. Min Act: -0.0000

Data Index: 1040364 (C4 (Web Text))

Max Activating Token Index: 918