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

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

Neuron 1620 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0505. Min Act: -0.0001

Data Index: 1279748 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0547. Min Act: -0.0001

Data Index: 1223692 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1055700 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0362. Min Act: -0.0001

Data Index: 805926 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0359. Min Act: -0.0001

Data Index: 455184 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0344. Min Act: -0.0001

Data Index: 322592 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0330. Min Act: -0.0001

Data Index: 804225 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0328. Min Act: -0.0001

Data Index: 731853 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0357. Min Act: -0.0001

Data Index: 1036305 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0322. Min Act: -0.0001

Data Index: 466129 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0314. Min Act: -0.0001

Data Index: 223362 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0302. Min Act: -0.0001

Data Index: 499340 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1356766 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0317. Min Act: -0.0001

Data Index: 942473 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0302. Min Act: -0.0001

Data Index: 181879 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0299. Min Act: -0.0001

Data Index: 1114090 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0289. Min Act: -0.0001

Data Index: 390916 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0298. Min Act: -0.0001

Data Index: 21726 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0280. Min Act: -0.0001

Data Index: 684982 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0276. Min Act: -0.0001

Data Index: 795464 (C4 (Web Text))

Max Activating Token Index: 538