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

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

Neuron 433 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: 1.2201. Min Range: -1.2201

Max Act: 1.2201. Min Act: -0.0000

Data Index: 1528733 (Python Code)

Max Activating Token Index: 417

Text #1

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.9452. Min Act: -0.0000

Data Index: 665629 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.9051. Min Act: -0.0000

Data Index: 619062 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.8679. Min Act: -0.0000

Data Index: 1587109 (Python Code)

Max Activating Token Index: 101

Text #4

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.8582. Min Act: -0.0000

Data Index: 1198137 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.8545. Min Act: -0.0000

Data Index: 1070598 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.8491. Min Act: -0.0000

Data Index: 639587 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.8503. Min Act: -0.0000

Data Index: 1488955 (Python Code)

Max Activating Token Index: 94

Text #8

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.7731. Min Act: -0.0000

Data Index: 1614057 (Python Code)

Max Activating Token Index: 38

Text #9

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.8288. Min Act: -0.0000

Data Index: 1244035 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1382524 (Python Code)

Max Activating Token Index: 41

Text #11

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.7322. Min Act: -0.0000

Data Index: 86177 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1389492 (Python Code)

Max Activating Token Index: 676

Text #13

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1627762 (Python Code)

Max Activating Token Index: 39

Text #14

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1493618 (Python Code)

Max Activating Token Index: 87

Text #15

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.7345. Min Act: -0.0000

Data Index: 110043 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.6863. Min Act: -0.0000

Data Index: 618121 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.6795. Min Act: -0.0000

Data Index: 374344 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1439594 (Python Code)

Max Activating Token Index: 770

Text #19

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1355163 (C4 (Web Text))

Max Activating Token Index: 262