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

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

Neuron 908 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1436. Min Range: -2.1436

Max Act: 2.1436. Min Act: -0.0000

Data Index: 466680 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 2.1436. Min Range: -2.1436

Max Act: 2.0635. Min Act: -0.0000

Data Index: 754373 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 2.1436. Min Range: -2.1436

Max Act: 1.8685. Min Act: -0.0000

Data Index: 1033433 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 2.1436. Min Range: -2.1436

Max Act: 1.6353. Min Act: -0.0000

Data Index: 603694 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 2.1436. Min Range: -2.1436

Max Act: 1.4913. Min Act: -0.0000

Data Index: 403306 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 2.1436. Min Range: -2.1436

Max Act: 1.4101. Min Act: -0.0000

Data Index: 853960 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 2.1436. Min Range: -2.1436

Max Act: 1.1649. Min Act: -0.0000

Data Index: 405018 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 2.1436. Min Range: -2.1436

Max Act: 1.1554. Min Act: -0.0000

Data Index: 932002 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 2.1436. Min Range: -2.1436

Max Act: 1.0927. Min Act: -0.0000

Data Index: 756097 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 2.1436. Min Range: -2.1436

Max Act: 1.1038. Min Act: -0.0000

Data Index: 760524 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 2.1436. Min Range: -2.1436

Max Act: 1.0555. Min Act: -0.0000

Data Index: 249558 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 2.1436. Min Range: -2.1436

Max Act: 0.9821. Min Act: -0.0000

Data Index: 113104 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 2.1436. Min Range: -2.1436

Max Act: 1.0651. Min Act: -0.0000

Data Index: 446706 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 2.1436. Min Range: -2.1436

Max Act: 1.0231. Min Act: -0.0000

Data Index: 288333 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 2.1436. Min Range: -2.1436

Max Act: 0.9671. Min Act: -0.0000

Data Index: 1148106 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 2.1436. Min Range: -2.1436

Max Act: 1.0241. Min Act: -0.0000

Data Index: 812517 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 2.1436. Min Range: -2.1436

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1234178 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 2.1436. Min Range: -2.1436

Max Act: 1.0183. Min Act: -0.0000

Data Index: 1281757 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 2.1436. Min Range: -2.1436

Max Act: 1.0214. Min Act: -0.0000

Data Index: 541274 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 2.1436. Min Range: -2.1436

Max Act: 0.9591. Min Act: -0.0000

Data Index: 1252103 (C4 (Web Text))

Max Activating Token Index: 902