Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2885 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1787. Min Range: -2.1787

Max Act: 2.1787. Min Act: -0.0000

Data Index: 1233337 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 2.1787. Min Range: -2.1787

Max Act: 2.0395. Min Act: -0.0000

Data Index: 514332 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.9143. Min Act: -0.0000

Data Index: 1204111 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.8751. Min Act: -0.0000

Data Index: 677404 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.7369. Min Act: -0.0000

Data Index: 898329 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.8212. Min Act: -0.0000

Data Index: 762314 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.6236. Min Act: -0.0000

Data Index: 773462 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.6740. Min Act: -0.0000

Data Index: 85031 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.6820. Min Act: -0.0000

Data Index: 329926 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.7578. Min Act: -0.0000

Data Index: 662096 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.6518. Min Act: -0.0000

Data Index: 72341 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.5262. Min Act: -0.0000

Data Index: 670657 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.5391. Min Act: -0.0000

Data Index: 914318 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.4572. Min Act: -0.0000

Data Index: 398113 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.5223. Min Act: -0.0000

Data Index: 651348 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.4636. Min Act: -0.0000

Data Index: 478541 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.3645. Min Act: -0.0000

Data Index: 568386 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.4939. Min Act: -0.0000

Data Index: 106674 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.4077. Min Act: -0.0000

Data Index: 848056 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.3188. Min Act: -0.0000

Data Index: 1170655 (C4 (Web Text))

Max Activating Token Index: 247