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

Dataset: The Pile

Neuron 2106 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3206. Min Act: -0.0000

Data Index: 303201 (The Pile)

Max Activating Token Index: 605

Text #1

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3488. Min Act: -0.0000

Data Index: 1336214 (The Pile)

Max Activating Token Index: 1004

Text #2

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1060672 (The Pile)

Max Activating Token Index: 717

Text #3

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3414. Min Act: -0.0000

Data Index: 1474423 (The Pile)

Max Activating Token Index: 300

Text #4

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3341. Min Act: -0.0000

Data Index: 1215878 (The Pile)

Max Activating Token Index: 385

Text #5

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3323. Min Act: -0.0000

Data Index: 33256 (The Pile)

Max Activating Token Index: 639

Text #6

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3553. Min Act: -0.0000

Data Index: 949258 (The Pile)

Max Activating Token Index: 666

Text #7

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1293917 (The Pile)

Max Activating Token Index: 339

Text #8

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3252. Min Act: -0.0000

Data Index: 1398737 (The Pile)

Max Activating Token Index: 446

Text #9

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3354. Min Act: -0.0000

Data Index: 1302893 (The Pile)

Max Activating Token Index: 612

Text #10

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3225. Min Act: -0.0000

Data Index: 1884622 (The Pile)

Max Activating Token Index: 911

Text #11

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2910. Min Act: -0.0000

Data Index: 1942388 (The Pile)

Max Activating Token Index: 888

Text #12

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1660446 (The Pile)

Max Activating Token Index: 809

Text #13

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1270463 (The Pile)

Max Activating Token Index: 895

Text #14

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3354. Min Act: -0.0000

Data Index: 787811 (The Pile)

Max Activating Token Index: 81

Text #15

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3228. Min Act: -0.0000

Data Index: 1074209 (The Pile)

Max Activating Token Index: 573

Text #16

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3052. Min Act: -0.0000

Data Index: 238640 (The Pile)

Max Activating Token Index: 465

Text #17

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3358. Min Act: -0.0000

Data Index: 44727 (The Pile)

Max Activating Token Index: 726

Text #18

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2961. Min Act: -0.0000

Data Index: 1903322 (The Pile)

Max Activating Token Index: 945

Text #19

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3140. Min Act: -0.0000

Data Index: 1042466 (The Pile)

Max Activating Token Index: 793