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

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

Neuron 33 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: 5.3545. Min Range: -5.3545

Max Act: 5.3276. Min Act: -0.0001

Data Index: 222450 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 5.3545. Min Range: -5.3545

Max Act: 5.2260. Min Act: -0.0001

Data Index: 645071 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 5.3545. Min Range: -5.3545

Max Act: 5.3545. Min Act: -0.0001

Data Index: 292691 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 5.3545. Min Range: -5.3545

Max Act: 4.9920. Min Act: -0.0001

Data Index: 1198253 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 5.3545. Min Range: -5.3545

Max Act: 5.1954. Min Act: -0.0001

Data Index: 701921 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 5.3545. Min Range: -5.3545

Max Act: 5.3187. Min Act: -0.0001

Data Index: 98981 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 5.3545. Min Range: -5.3545

Max Act: 5.0008. Min Act: -0.0001

Data Index: 832889 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 5.3545. Min Range: -5.3545

Max Act: 5.1220. Min Act: -0.0001

Data Index: 48995 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 5.3545. Min Range: -5.3545

Max Act: 4.7339. Min Act: -0.0001

Data Index: 1234598 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 5.3545. Min Range: -5.3545

Max Act: 4.7621. Min Act: -0.0001

Data Index: 573030 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 5.3545. Min Range: -5.3545

Max Act: 4.6498. Min Act: -0.0001

Data Index: 1135280 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 5.3545. Min Range: -5.3545

Max Act: 4.5889. Min Act: -0.0001

Data Index: 920574 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 5.3545. Min Range: -5.3545

Max Act: 4.5600. Min Act: -0.0001

Data Index: 422284 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 5.3545. Min Range: -5.3545

Max Act: 4.5162. Min Act: -0.0001

Data Index: 607873 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 5.3545. Min Range: -5.3545

Max Act: 4.3156. Min Act: -0.0001

Data Index: 159541 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 5.3545. Min Range: -5.3545

Max Act: 4.3306. Min Act: -0.0000

Data Index: 1619615 (Python Code)

Max Activating Token Index: 883

Text #16

Max Range: 5.3545. Min Range: -5.3545

Max Act: 3.8631. Min Act: -0.0001

Data Index: 561773 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 5.3545. Min Range: -5.3545

Max Act: 4.1452. Min Act: -0.0001

Data Index: 1192596 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 5.3545. Min Range: -5.3545

Max Act: 4.1403. Min Act: -0.0001

Data Index: 432371 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 5.3545. Min Range: -5.3545

Max Act: 4.2600. Min Act: -0.0001

Data Index: 1323403 (C4 (Web Text))

Max Activating Token Index: 611