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

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

Neuron 3407 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3353. Min Range: -1.3353

Max Act: 1.3353. Min Act: 0.0000

Data Index: 861280 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 1.3353. Min Range: -1.3353

Max Act: 1.1364. Min Act: 0.0000

Data Index: 1429615 (Python Code)

Max Activating Token Index: 817

Text #2

Max Range: 1.3353. Min Range: -1.3353

Max Act: 1.1247. Min Act: -0.0000

Data Index: 866020 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 1.3353. Min Range: -1.3353

Max Act: 1.1058. Min Act: -0.0000

Data Index: 96975 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 1.3353. Min Range: -1.3353

Max Act: 1.0423. Min Act: -0.0000

Data Index: 85497 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 1.3353. Min Range: -1.3353

Max Act: 1.0548. Min Act: 0.0000

Data Index: 152127 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 1.3353. Min Range: -1.3353

Max Act: 1.0422. Min Act: 0.0001

Data Index: 1469458 (Python Code)

Max Activating Token Index: 42

Text #7

Max Range: 1.3353. Min Range: -1.3353

Max Act: 1.0339. Min Act: -0.0000

Data Index: 1435491 (Python Code)

Max Activating Token Index: 737

Text #8

Max Range: 1.3353. Min Range: -1.3353

Max Act: 1.0162. Min Act: -0.0000

Data Index: 972991 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 1.3353. Min Range: -1.3353

Max Act: 1.0025. Min Act: -0.0000

Data Index: 675878 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.9922. Min Act: 0.0001

Data Index: 1651044 (Python Code)

Max Activating Token Index: 50

Text #11

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.8868. Min Act: 0.0001

Data Index: 1578063 (Python Code)

Max Activating Token Index: 969

Text #12

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.9478. Min Act: -0.0000

Data Index: 1591218 (Python Code)

Max Activating Token Index: 346

Text #13

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.9702. Min Act: -0.0000

Data Index: 564169 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.9584. Min Act: -0.0000

Data Index: 741071 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.9317. Min Act: 0.0001

Data Index: 961897 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.9757. Min Act: -0.0000

Data Index: 137271 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.9191. Min Act: 0.0000

Data Index: 1089166 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.9071. Min Act: -0.0000

Data Index: 281496 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.9286. Min Act: -0.0000

Data Index: 35476 (C4 (Web Text))

Max Activating Token Index: 593