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

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

Neuron 2014 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.2366. Min Range: -1.2366

Max Act: 1.2366. Min Act: -0.0002

Data Index: 340705 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 1.2366. Min Range: -1.2366

Max Act: 1.2155. Min Act: -0.0002

Data Index: 755776 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 1.2366. Min Range: -1.2366

Max Act: 1.0906. Min Act: -0.0002

Data Index: 1166416 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 1.2366. Min Range: -1.2366

Max Act: 1.0973. Min Act: -0.0002

Data Index: 224054 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 1.2366. Min Range: -1.2366

Max Act: 1.0291. Min Act: -0.0002

Data Index: 1541701 (Python Code)

Max Activating Token Index: 27

Text #5

Max Range: 1.2366. Min Range: -1.2366

Max Act: 1.0362. Min Act: -0.0002

Data Index: 796085 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 1.2366. Min Range: -1.2366

Max Act: 1.0206. Min Act: -0.0003

Data Index: 325388 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 1.2366. Min Range: -1.2366

Max Act: 1.0750. Min Act: -0.0002

Data Index: 1250020 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 1.2366. Min Range: -1.2366

Max Act: 1.0443. Min Act: -0.0002

Data Index: 134395 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 1.2366. Min Range: -1.2366

Max Act: 1.0227. Min Act: -0.0002

Data Index: 189338 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 1.2366. Min Range: -1.2366

Max Act: 0.9914. Min Act: -0.0002

Data Index: 1638221 (Python Code)

Max Activating Token Index: 67

Text #11

Max Range: 1.2366. Min Range: -1.2366

Max Act: 1.0102. Min Act: -0.0002

Data Index: 771223 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 1.2366. Min Range: -1.2366

Max Act: 1.0117. Min Act: -0.0002

Data Index: 928513 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 1.2366. Min Range: -1.2366

Max Act: 1.0002. Min Act: -0.0002

Data Index: 745990 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 1.2366. Min Range: -1.2366

Max Act: 0.9806. Min Act: -0.0002

Data Index: 1130586 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 1.2366. Min Range: -1.2366

Max Act: 0.9888. Min Act: -0.0002

Data Index: 461872 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 1.2366. Min Range: -1.2366

Max Act: 0.9623. Min Act: -0.0002

Data Index: 1090718 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 1.2366. Min Range: -1.2366

Max Act: 0.9574. Min Act: -0.0002

Data Index: 977414 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 1.2366. Min Range: -1.2366

Max Act: 0.9523. Min Act: -0.0002

Data Index: 1276244 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 1.2366. Min Range: -1.2366

Max Act: 0.9590. Min Act: -0.0002

Data Index: 520845 (C4 (Web Text))

Max Activating Token Index: 88