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

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

Neuron 2585 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0987. Min Range: -1.0987

Max Act: 1.0987. Min Act: 0.0000

Data Index: 536805 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.9804. Min Act: -0.0000

Data Index: 906178 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 1.0987. Min Range: -1.0987

Max Act: 1.0308. Min Act: -0.0000

Data Index: 338042 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.9749. Min Act: -0.0000

Data Index: 1148430 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.9103. Min Act: -0.0000

Data Index: 4275 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.8737. Min Act: -0.0000

Data Index: 39665 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.9144. Min Act: -0.0000

Data Index: 1350442 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.8432. Min Act: -0.0000

Data Index: 572556 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.8366. Min Act: -0.0000

Data Index: 1329753 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.8427. Min Act: -0.0000

Data Index: 470665 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.8369. Min Act: -0.0000

Data Index: 976054 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.8163. Min Act: -0.0000

Data Index: 710762 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.8125. Min Act: -0.0000

Data Index: 568507 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1251763 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.7973. Min Act: -0.0000

Data Index: 1203904 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.8384. Min Act: -0.0000

Data Index: 838802 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.7841. Min Act: -0.0000

Data Index: 548980 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.7976. Min Act: 0.0000

Data Index: 19365 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.7849. Min Act: -0.0000

Data Index: 657468 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.7717. Min Act: -0.0000

Data Index: 1320476 (C4 (Web Text))

Max Activating Token Index: 799