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

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

Neuron 5342 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3401. Min Range: -1.3401

Max Act: 1.3401. Min Act: -0.0001

Data Index: 322529 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 1.3401. Min Range: -1.3401

Max Act: 1.0368. Min Act: -0.0001

Data Index: 684623 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.9611. Min Act: -0.0001

Data Index: 1646670 (Python Code)

Max Activating Token Index: 737

Text #3

Max Range: 1.3401. Min Range: -1.3401

Max Act: 1.0002. Min Act: -0.0001

Data Index: 1435211 (Python Code)

Max Activating Token Index: 943

Text #4

Max Range: 1.3401. Min Range: -1.3401

Max Act: 1.0463. Min Act: -0.0001

Data Index: 663128 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.8813. Min Act: -0.0000

Data Index: 11166 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.8884. Min Act: -0.0001

Data Index: 1269774 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 1.3401. Min Range: -1.3401

Max Act: 1.0010. Min Act: -0.0001

Data Index: 391273 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.8658. Min Act: -0.0001

Data Index: 1382766 (Python Code)

Max Activating Token Index: 425

Text #9

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.8565. Min Act: -0.0001

Data Index: 933217 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.9177. Min Act: -0.0001

Data Index: 1634899 (Python Code)

Max Activating Token Index: 672

Text #11

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.8878. Min Act: -0.0001

Data Index: 198965 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.8664. Min Act: -0.0001

Data Index: 412 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.8561. Min Act: -0.0001

Data Index: 784455 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.8513. Min Act: -0.0001

Data Index: 34563 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.8710. Min Act: -0.0001

Data Index: 867384 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.7361. Min Act: -0.0001

Data Index: 631692 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.8422. Min Act: -0.0001

Data Index: 9880 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.8205. Min Act: -0.0001

Data Index: 927364 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.7949. Min Act: -0.0001

Data Index: 824065 (C4 (Web Text))

Max Activating Token Index: 450