Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3863 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2294. Min Act: -0.0000

Data Index: 987236 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2162. Min Act: -0.0000

Data Index: 546117 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2273. Min Act: -0.0000

Data Index: 829425 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1924. Min Act: -0.0001

Data Index: 218628 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2241. Min Act: -0.0001

Data Index: 1203109 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2127. Min Act: -0.0000

Data Index: 320606 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1913. Min Act: -0.0000

Data Index: 357271 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1907. Min Act: -0.0001

Data Index: 216780 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1922. Min Act: -0.0000

Data Index: 850048 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1261447 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1912. Min Act: -0.0000

Data Index: 936222 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1755. Min Act: -0.0000

Data Index: 96967 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1871. Min Act: -0.0001

Data Index: 1495664 (Python Code)

Max Activating Token Index: 597

Text #13

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1778. Min Act: -0.0001

Data Index: 914610 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1701. Min Act: -0.0001

Data Index: 231649 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1687. Min Act: -0.0001

Data Index: 1612734 (Python Code)

Max Activating Token Index: 760

Text #16

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1563. Min Act: -0.0000

Data Index: 800663 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1647233 (Python Code)

Max Activating Token Index: 371

Text #18

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1654987 (Python Code)

Max Activating Token Index: 246

Text #19

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1706. Min Act: -0.0001

Data Index: 1606877 (Python Code)

Max Activating Token Index: 563