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

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

Neuron 1360 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4226. Min Range: -4.4226

Max Act: 4.2608. Min Act: -0.0000

Data Index: 1563146 (Python Code)

Max Activating Token Index: 307

Text #1

Max Range: 4.4226. Min Range: -4.4226

Max Act: 4.3648. Min Act: -0.0000

Data Index: 1413874 (Python Code)

Max Activating Token Index: 1018

Text #2

Max Range: 4.4226. Min Range: -4.4226

Max Act: 4.1244. Min Act: -0.0000

Data Index: 1551555 (Python Code)

Max Activating Token Index: 615

Text #3

Max Range: 4.4226. Min Range: -4.4226

Max Act: 3.9287. Min Act: -0.0000

Data Index: 1576970 (Python Code)

Max Activating Token Index: 705

Text #4

Max Range: 4.4226. Min Range: -4.4226

Max Act: 4.4226. Min Act: -0.0000

Data Index: 1417448 (Python Code)

Max Activating Token Index: 186

Text #5

Max Range: 4.4226. Min Range: -4.4226

Max Act: 3.8151. Min Act: -0.0000

Data Index: 1512482 (Python Code)

Max Activating Token Index: 952

Text #6

Max Range: 4.4226. Min Range: -4.4226

Max Act: 3.8481. Min Act: -0.0000

Data Index: 1435437 (Python Code)

Max Activating Token Index: 356

Text #7

Max Range: 4.4226. Min Range: -4.4226

Max Act: 3.7310. Min Act: -0.0000

Data Index: 1585319 (Python Code)

Max Activating Token Index: 854

Text #8

Max Range: 4.4226. Min Range: -4.4226

Max Act: 3.8818. Min Act: -0.0000

Data Index: 1558864 (Python Code)

Max Activating Token Index: 66

Text #9

Max Range: 4.4226. Min Range: -4.4226

Max Act: 3.6261. Min Act: -0.0000

Data Index: 1460019 (Python Code)

Max Activating Token Index: 652

Text #10

Max Range: 4.4226. Min Range: -4.4226

Max Act: 3.7379. Min Act: -0.0000

Data Index: 1158184 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 4.4226. Min Range: -4.4226

Max Act: 3.3931. Min Act: -0.0000

Data Index: 1614816 (Python Code)

Max Activating Token Index: 362

Text #12

Max Range: 4.4226. Min Range: -4.4226

Max Act: 3.4976. Min Act: -0.0000

Data Index: 1543470 (Python Code)

Max Activating Token Index: 677

Text #13

Max Range: 4.4226. Min Range: -4.4226

Max Act: 3.4426. Min Act: -0.0000

Data Index: 1567235 (Python Code)

Max Activating Token Index: 545

Text #14

Max Range: 4.4226. Min Range: -4.4226

Max Act: 3.5027. Min Act: -0.0000

Data Index: 1597304 (Python Code)

Max Activating Token Index: 34

Text #15

Max Range: 4.4226. Min Range: -4.4226

Max Act: 3.1717. Min Act: -0.0000

Data Index: 1578842 (Python Code)

Max Activating Token Index: 294

Text #16

Max Range: 4.4226. Min Range: -4.4226

Max Act: 3.3000. Min Act: -0.0000

Data Index: 1370822 (Python Code)

Max Activating Token Index: 37

Text #17

Max Range: 4.4226. Min Range: -4.4226

Max Act: 3.1353. Min Act: -0.0000

Data Index: 1465365 (Python Code)

Max Activating Token Index: 216

Text #18

Max Range: 4.4226. Min Range: -4.4226

Max Act: 3.2965. Min Act: -0.0000

Data Index: 1638065 (Python Code)

Max Activating Token Index: 825

Text #19

Max Range: 4.4226. Min Range: -4.4226

Max Act: 3.1933. Min Act: -0.0000

Data Index: 1650355 (Python Code)

Max Activating Token Index: 833