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

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

Neuron 5118 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1370367 (Python Code)

Max Activating Token Index: 777

Text #1

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1588022 (Python Code)

Max Activating Token Index: 535

Text #2

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1451856 (Python Code)

Max Activating Token Index: 128

Text #3

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1025927 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1063228 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1152859 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0310. Min Act: -0.0002

Data Index: 765178 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1563157 (Python Code)

Max Activating Token Index: 81

Text #8

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1106750 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0302. Min Act: -0.0002

Data Index: 996240 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0286. Min Act: -0.0002

Data Index: 25172 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0289. Min Act: -0.0002

Data Index: 136358 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1292423 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1636505 (Python Code)

Max Activating Token Index: 394

Text #14

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0265. Min Act: -0.0002

Data Index: 739136 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0286. Min Act: -0.0002

Data Index: 20167 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0279. Min Act: -0.0002

Data Index: 911062 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1077794 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0271. Min Act: -0.0002

Data Index: 1471788 (Python Code)

Max Activating Token Index: 478

Text #19

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0263. Min Act: -0.0002

Data Index: 666668 (C4 (Web Text))

Max Activating Token Index: 77