Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1556 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0675. Min Act: -0.0003

Data Index: 832848 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0590. Min Act: -0.0003

Data Index: 1174517 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0573. Min Act: -0.0003

Data Index: 183990 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0531. Min Act: -0.0003

Data Index: 688504 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0540. Min Act: -0.0003

Data Index: 115405 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0547. Min Act: -0.0003

Data Index: 476189 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0519. Min Act: -0.0004

Data Index: 38960 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1018375 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0524. Min Act: -0.0003

Data Index: 858279 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0497. Min Act: -0.0003

Data Index: 1027162 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0519. Min Act: -0.0003

Data Index: 300887 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1024708 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0502. Min Act: -0.0003

Data Index: 797458 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0501. Min Act: -0.0003

Data Index: 508733 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0498. Min Act: -0.0003

Data Index: 465140 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0485. Min Act: -0.0003

Data Index: 62357 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0504. Min Act: -0.0002

Data Index: 169639 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0490. Min Act: -0.0004

Data Index: 810640 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0481. Min Act: -0.0003

Data Index: 858323 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0498. Min Act: -0.0003

Data Index: 939707 (C4 (Web Text))

Max Activating Token Index: 413