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

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

Neuron 4718 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: 0.5707. Min Range: -0.5707

Max Act: 0.5707. Min Act: -0.0000

Data Index: 136064 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.5214. Min Act: -0.0000

Data Index: 924739 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4979. Min Act: -0.0000

Data Index: 247564 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.5005. Min Act: -0.0000

Data Index: 1270725 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4760. Min Act: -0.0000

Data Index: 116775 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1100077 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4708. Min Act: -0.0000

Data Index: 251377 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4747. Min Act: -0.0000

Data Index: 408575 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4708. Min Act: -0.0000

Data Index: 49031 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4642. Min Act: -0.0000

Data Index: 697577 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4475. Min Act: -0.0000

Data Index: 666340 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4618. Min Act: -0.0000

Data Index: 1315770 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4434. Min Act: -0.0000

Data Index: 83560 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4520. Min Act: -0.0000

Data Index: 150121 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4473. Min Act: -0.0000

Data Index: 214955 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4143. Min Act: -0.0000

Data Index: 117719 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1007441 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4257. Min Act: -0.0000

Data Index: 307436 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1172020 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4225. Min Act: -0.0000

Data Index: 634420 (C4 (Web Text))

Max Activating Token Index: 981