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

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

Neuron 682 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: 0.0782. Min Range: -0.0782

Max Act: 0.0782. Min Act: -0.0000

Data Index: 264449 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0641. Min Act: -0.0000

Data Index: 183559 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0765. Min Act: -0.0000

Data Index: 95763 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0675. Min Act: -0.0000

Data Index: 388883 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0600. Min Act: -0.0001

Data Index: 1123171 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0649. Min Act: -0.0000

Data Index: 974427 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1542634 (Python Code)

Max Activating Token Index: 176

Text #7

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0603. Min Act: -0.0000

Data Index: 124615 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0589. Min Act: -0.0000

Data Index: 274092 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1251810 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0555. Min Act: -0.0000

Data Index: 584979 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0590. Min Act: -0.0000

Data Index: 1105794 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0629. Min Act: -0.0000

Data Index: 926343 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0631. Min Act: -0.0000

Data Index: 273394 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0501. Min Act: -0.0000

Data Index: 1454093 (Python Code)

Max Activating Token Index: 365

Text #15

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0567. Min Act: -0.0000

Data Index: 259792 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1078510 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0584. Min Act: -0.0001

Data Index: 554023 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0617. Min Act: -0.0001

Data Index: 1028490 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0559. Min Act: -0.0001

Data Index: 1190700 (C4 (Web Text))

Max Activating Token Index: 757