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

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

Neuron 78 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6009. Min Range: -2.6009

Max Act: 2.6009. Min Act: -0.0000

Data Index: 26567 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 2.6009. Min Range: -2.6009

Max Act: 2.5895. Min Act: -0.0000

Data Index: 1214643 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 2.6009. Min Range: -2.6009

Max Act: 2.5744. Min Act: -0.0000

Data Index: 449109 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 2.6009. Min Range: -2.6009

Max Act: 2.3144. Min Act: -0.0000

Data Index: 1339646 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 2.6009. Min Range: -2.6009

Max Act: 2.3298. Min Act: -0.0000

Data Index: 385922 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 2.6009. Min Range: -2.6009

Max Act: 2.2888. Min Act: -0.0000

Data Index: 563237 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 2.6009. Min Range: -2.6009

Max Act: 2.2106. Min Act: -0.0000

Data Index: 711442 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 2.6009. Min Range: -2.6009

Max Act: 2.0515. Min Act: -0.0000

Data Index: 254827 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 2.6009. Min Range: -2.6009

Max Act: 2.1397. Min Act: -0.0000

Data Index: 941385 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 2.6009. Min Range: -2.6009

Max Act: 2.0064. Min Act: -0.0000

Data Index: 1194087 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 2.6009. Min Range: -2.6009

Max Act: 2.1021. Min Act: -0.0000

Data Index: 47876 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 2.6009. Min Range: -2.6009

Max Act: 2.0264. Min Act: -0.0000

Data Index: 947607 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 2.6009. Min Range: -2.6009

Max Act: 2.0440. Min Act: -0.0000

Data Index: 1051698 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 2.6009. Min Range: -2.6009

Max Act: 2.0311. Min Act: -0.0000

Data Index: 817802 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 2.6009. Min Range: -2.6009

Max Act: 1.8911. Min Act: -0.0000

Data Index: 130017 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 2.6009. Min Range: -2.6009

Max Act: 1.9057. Min Act: -0.0000

Data Index: 1347521 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 2.6009. Min Range: -2.6009

Max Act: 2.0472. Min Act: -0.0000

Data Index: 1353290 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 2.6009. Min Range: -2.6009

Max Act: 1.9772. Min Act: -0.0000

Data Index: 69199 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 2.6009. Min Range: -2.6009

Max Act: 1.9383. Min Act: -0.0000

Data Index: 940220 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 2.6009. Min Range: -2.6009

Max Act: 1.9039. Min Act: -0.0000

Data Index: 1131388 (C4 (Web Text))

Max Activating Token Index: 943