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

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

Neuron 2690 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: 2.3588. Min Range: -2.3588

Max Act: 2.3588. Min Act: -0.0000

Data Index: 1265589 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 2.3588. Min Range: -2.3588

Max Act: 2.2212. Min Act: -0.0000

Data Index: 977173 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 2.3588. Min Range: -2.3588

Max Act: 2.1825. Min Act: -0.0000

Data Index: 910451 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 2.3588. Min Range: -2.3588

Max Act: 2.1295. Min Act: -0.0000

Data Index: 884177 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 2.3588. Min Range: -2.3588

Max Act: 2.2209. Min Act: -0.0000

Data Index: 308722 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 2.3588. Min Range: -2.3588

Max Act: 2.2053. Min Act: -0.0000

Data Index: 1228105 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 2.3588. Min Range: -2.3588

Max Act: 1.9908. Min Act: -0.0000

Data Index: 98828 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 2.3588. Min Range: -2.3588

Max Act: 1.9164. Min Act: -0.0000

Data Index: 258539 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 2.3588. Min Range: -2.3588

Max Act: 2.0249. Min Act: -0.0000

Data Index: 892262 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 2.3588. Min Range: -2.3588

Max Act: 2.1372. Min Act: -0.0000

Data Index: 324357 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 2.3588. Min Range: -2.3588

Max Act: 2.0086. Min Act: -0.0000

Data Index: 152503 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 2.3588. Min Range: -2.3588

Max Act: 1.8829. Min Act: -0.0000

Data Index: 461143 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 2.3588. Min Range: -2.3588

Max Act: 1.8768. Min Act: -0.0000

Data Index: 1641889 (Python Code)

Max Activating Token Index: 992

Text #13

Max Range: 2.3588. Min Range: -2.3588

Max Act: 1.9699. Min Act: -0.0000

Data Index: 1567479 (Python Code)

Max Activating Token Index: 33

Text #14

Max Range: 2.3588. Min Range: -2.3588

Max Act: 2.0663. Min Act: -0.0000

Data Index: 641521 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 2.3588. Min Range: -2.3588

Max Act: 1.9357. Min Act: -0.0000

Data Index: 133064 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 2.3588. Min Range: -2.3588

Max Act: 1.9251. Min Act: -0.0000

Data Index: 996556 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 2.3588. Min Range: -2.3588

Max Act: 1.9011. Min Act: -0.0000

Data Index: 920282 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 2.3588. Min Range: -2.3588

Max Act: 1.8712. Min Act: -0.0000

Data Index: 1153655 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 2.3588. Min Range: -2.3588

Max Act: 1.7731. Min Act: -0.0000

Data Index: 176963 (C4 (Web Text))

Max Activating Token Index: 11