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

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

Neuron 4772 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0829. Min Act: -0.0002

Data Index: 507246 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1134998 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0568. Min Act: -0.0002

Data Index: 856431 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1167687 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0501. Min Act: -0.0002

Data Index: 774680 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0442. Min Act: -0.0002

Data Index: 241133 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1220440 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0469. Min Act: -0.0002

Data Index: 253902 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0483. Min Act: -0.0002

Data Index: 550457 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0464. Min Act: -0.0002

Data Index: 958491 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0477. Min Act: -0.0002

Data Index: 13144 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1228139 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0460. Min Act: -0.0002

Data Index: 577219 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0354. Min Act: -0.0002

Data Index: 428261 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1110794 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0434. Min Act: -0.0002

Data Index: 615621 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1155977 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0399. Min Act: -0.0002

Data Index: 406536 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0484. Min Act: -0.0002

Data Index: 500669 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0464. Min Act: -0.0002

Data Index: 75140 (C4 (Web Text))

Max Activating Token Index: 831