Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1447 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3345. Min Range: -1.3345

Max Act: 1.3345. Min Act: -0.0000

Data Index: 869447 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 1.3345. Min Range: -1.3345

Max Act: 1.2139. Min Act: -0.0000

Data Index: 153367 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 1.3345. Min Range: -1.3345

Max Act: 1.1293. Min Act: -0.0000

Data Index: 442394 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 1.3345. Min Range: -1.3345

Max Act: 1.0658. Min Act: -0.0000

Data Index: 751138 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 1.3345. Min Range: -1.3345

Max Act: 1.0326. Min Act: -0.0000

Data Index: 768860 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 1.3345. Min Range: -1.3345

Max Act: 1.0130. Min Act: -0.0000

Data Index: 799079 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 1.3345. Min Range: -1.3345

Max Act: 0.9676. Min Act: -0.0000

Data Index: 170719 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 1.3345. Min Range: -1.3345

Max Act: 0.9929. Min Act: 0.0000

Data Index: 593227 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 1.3345. Min Range: -1.3345

Max Act: 0.9440. Min Act: -0.0000

Data Index: 727723 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 1.3345. Min Range: -1.3345

Max Act: 0.9497. Min Act: -0.0000

Data Index: 470243 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 1.3345. Min Range: -1.3345

Max Act: 0.9236. Min Act: 0.0000

Data Index: 286327 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 1.3345. Min Range: -1.3345

Max Act: 0.9229. Min Act: 0.0000

Data Index: 1013254 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 1.3345. Min Range: -1.3345

Max Act: 0.9315. Min Act: -0.0000

Data Index: 755368 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 1.3345. Min Range: -1.3345

Max Act: 0.9010. Min Act: -0.0000

Data Index: 390064 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 1.3345. Min Range: -1.3345

Max Act: 0.8712. Min Act: -0.0000

Data Index: 618683 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 1.3345. Min Range: -1.3345

Max Act: 0.8984. Min Act: -0.0000

Data Index: 687666 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 1.3345. Min Range: -1.3345

Max Act: 0.8898. Min Act: 0.0000

Data Index: 1002792 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 1.3345. Min Range: -1.3345

Max Act: 0.8085. Min Act: -0.0000

Data Index: 64641 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 1.3345. Min Range: -1.3345

Max Act: 0.8733. Min Act: 0.0000

Data Index: 948220 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 1.3345. Min Range: -1.3345

Max Act: 0.8623. Min Act: -0.0000

Data Index: 689294 (C4 (Web Text))

Max Activating Token Index: 827