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

Dataset: The Pile

Neuron 36 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: 3.3553. Min Range: -3.3553

Max Act: 3.3553. Min Act: -0.0000

Data Index: 1373462 (The Pile)

Max Activating Token Index: 876

Text #1

Max Range: 3.3553. Min Range: -3.3553

Max Act: 3.3067. Min Act: -0.0000

Data Index: 1303320 (The Pile)

Max Activating Token Index: 1002

Text #2

Max Range: 3.3553. Min Range: -3.3553

Max Act: 3.2378. Min Act: -0.0000

Data Index: 694105 (The Pile)

Max Activating Token Index: 666

Text #3

Max Range: 3.3553. Min Range: -3.3553

Max Act: 3.0745. Min Act: -0.0000

Data Index: 1837806 (The Pile)

Max Activating Token Index: 889

Text #4

Max Range: 3.3553. Min Range: -3.3553

Max Act: 3.2429. Min Act: -0.0000

Data Index: 1158641 (The Pile)

Max Activating Token Index: 925

Text #5

Max Range: 3.3553. Min Range: -3.3553

Max Act: 3.2391. Min Act: -0.0000

Data Index: 198610 (The Pile)

Max Activating Token Index: 551

Text #6

Max Range: 3.3553. Min Range: -3.3553

Max Act: 3.0802. Min Act: -0.0000

Data Index: 1247531 (The Pile)

Max Activating Token Index: 492

Text #7

Max Range: 3.3553. Min Range: -3.3553

Max Act: 3.2205. Min Act: -0.0000

Data Index: 847181 (The Pile)

Max Activating Token Index: 343

Text #8

Max Range: 3.3553. Min Range: -3.3553

Max Act: 2.9053. Min Act: -0.0000

Data Index: 261654 (The Pile)

Max Activating Token Index: 685

Text #9

Max Range: 3.3553. Min Range: -3.3553

Max Act: 3.0165. Min Act: -0.0000

Data Index: 1179956 (The Pile)

Max Activating Token Index: 407

Text #10

Max Range: 3.3553. Min Range: -3.3553

Max Act: 2.7943. Min Act: -0.0000

Data Index: 1336968 (The Pile)

Max Activating Token Index: 323

Text #11

Max Range: 3.3553. Min Range: -3.3553

Max Act: 2.9100. Min Act: -0.0000

Data Index: 1952102 (The Pile)

Max Activating Token Index: 674

Text #12

Max Range: 3.3553. Min Range: -3.3553

Max Act: 2.9195. Min Act: -0.0000

Data Index: 310914 (The Pile)

Max Activating Token Index: 206

Text #13

Max Range: 3.3553. Min Range: -3.3553

Max Act: 2.9216. Min Act: -0.0000

Data Index: 1813048 (The Pile)

Max Activating Token Index: 573

Text #14

Max Range: 3.3553. Min Range: -3.3553

Max Act: 2.8442. Min Act: -0.0000

Data Index: 984316 (The Pile)

Max Activating Token Index: 101

Text #15

Max Range: 3.3553. Min Range: -3.3553

Max Act: 2.8044. Min Act: -0.0000

Data Index: 137969 (The Pile)

Max Activating Token Index: 645

Text #16

Max Range: 3.3553. Min Range: -3.3553

Max Act: 3.2158. Min Act: -0.0000

Data Index: 1727080 (The Pile)

Max Activating Token Index: 763

Text #17

Max Range: 3.3553. Min Range: -3.3553

Max Act: 2.7875. Min Act: -0.0000

Data Index: 1479463 (The Pile)

Max Activating Token Index: 487

Text #18

Max Range: 3.3553. Min Range: -3.3553

Max Act: 3.0830. Min Act: -0.0000

Data Index: 1943402 (The Pile)

Max Activating Token Index: 613

Text #19

Max Range: 3.3553. Min Range: -3.3553

Max Act: 2.9242. Min Act: -0.0000

Data Index: 1165773 (The Pile)

Max Activating Token Index: 732