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

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

Neuron 3522 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.4748. Min Act: -0.0001

Data Index: 1284502 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.4414. Min Act: -0.0001

Data Index: 720470 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.3040. Min Act: -0.0000

Data Index: 98543 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.2899. Min Act: -0.0001

Data Index: 1341794 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.2447. Min Act: -0.0001

Data Index: 718816 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1670. Min Act: -0.0001

Data Index: 1207195 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1553. Min Act: -0.0000

Data Index: 960804 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0760. Min Act: -0.0001

Data Index: 587945 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0448. Min Act: -0.0000

Data Index: 282186 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0612. Min Act: -0.0001

Data Index: 1252062 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0128. Min Act: -0.0000

Data Index: 623448 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0234. Min Act: -0.0001

Data Index: 410318 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.9603. Min Act: -0.0001

Data Index: 1200454 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.9234. Min Act: -0.0001

Data Index: 322137 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.9319. Min Act: -0.0001

Data Index: 1324708 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.9250. Min Act: -0.0000

Data Index: 570300 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.9189. Min Act: -0.0001

Data Index: 583044 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.9122. Min Act: -0.0000

Data Index: 654023 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.8997. Min Act: -0.0001

Data Index: 125346 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.9230. Min Act: -0.0001

Data Index: 1082680 (C4 (Web Text))

Max Activating Token Index: 324