Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2232 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4306. Min Range: -2.4306

Max Act: 2.4306. Min Act: -0.0000

Data Index: 299118 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 2.4306. Min Range: -2.4306

Max Act: 2.4049. Min Act: -0.0000

Data Index: 823856 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 2.4306. Min Range: -2.4306

Max Act: 2.1943. Min Act: -0.0000

Data Index: 580571 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 2.4306. Min Range: -2.4306

Max Act: 2.1908. Min Act: -0.0000

Data Index: 584276 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 2.4306. Min Range: -2.4306

Max Act: 1.9826. Min Act: -0.0000

Data Index: 1242692 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 2.4306. Min Range: -2.4306

Max Act: 1.9578. Min Act: -0.0000

Data Index: 694573 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 2.4306. Min Range: -2.4306

Max Act: 1.9303. Min Act: -0.0000

Data Index: 310154 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 2.4306. Min Range: -2.4306

Max Act: 1.8684. Min Act: -0.0000

Data Index: 667740 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 2.4306. Min Range: -2.4306

Max Act: 1.8753. Min Act: -0.0000

Data Index: 91839 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 2.4306. Min Range: -2.4306

Max Act: 1.9464. Min Act: -0.0000

Data Index: 471007 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 2.4306. Min Range: -2.4306

Max Act: 1.8414. Min Act: -0.0000

Data Index: 252597 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 2.4306. Min Range: -2.4306

Max Act: 1.6317. Min Act: -0.0000

Data Index: 574485 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 2.4306. Min Range: -2.4306

Max Act: 1.8136. Min Act: -0.0000

Data Index: 30147 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 2.4306. Min Range: -2.4306

Max Act: 1.7159. Min Act: -0.0000

Data Index: 63612 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 2.4306. Min Range: -2.4306

Max Act: 1.6470. Min Act: -0.0000

Data Index: 317207 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 2.4306. Min Range: -2.4306

Max Act: 1.7397. Min Act: -0.0000

Data Index: 381305 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 2.4306. Min Range: -2.4306

Max Act: 1.7424. Min Act: -0.0000

Data Index: 865521 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 2.4306. Min Range: -2.4306

Max Act: 1.6433. Min Act: -0.0000

Data Index: 711218 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 2.4306. Min Range: -2.4306

Max Act: 1.6358. Min Act: -0.0000

Data Index: 48114 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 2.4306. Min Range: -2.4306

Max Act: 1.7339. Min Act: -0.0000

Data Index: 1069380 (C4 (Web Text))

Max Activating Token Index: 287