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

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

Neuron 1001 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.2254. Min Act: -0.0000

Data Index: 492057 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.2542. Min Act: -0.0000

Data Index: 1471637 (Python Code)

Max Activating Token Index: 965

Text #2

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.3263. Min Act: -0.0000

Data Index: 1435120 (Python Code)

Max Activating Token Index: 331

Text #3

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.2221. Min Act: -0.0000

Data Index: 1611276 (Python Code)

Max Activating Token Index: 114

Text #4

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.0796. Min Act: -0.0000

Data Index: 1198073 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.1515. Min Act: -0.0000

Data Index: 506256 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.0741. Min Act: -0.0000

Data Index: 1011918 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.2128. Min Act: -0.0000

Data Index: 1616253 (Python Code)

Max Activating Token Index: 875

Text #8

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.1308. Min Act: -0.0000

Data Index: 878703 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.0450. Min Act: -0.0000

Data Index: 426525 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.1410. Min Act: -0.0000

Data Index: 1641118 (Python Code)

Max Activating Token Index: 677

Text #11

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.0385. Min Act: -0.0000

Data Index: 553628 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.1271. Min Act: -0.0000

Data Index: 1576771 (Python Code)

Max Activating Token Index: 428

Text #13

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.0911. Min Act: -0.0000

Data Index: 1522071 (Python Code)

Max Activating Token Index: 624

Text #14

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.0646. Min Act: -0.0000

Data Index: 1459676 (Python Code)

Max Activating Token Index: 215

Text #15

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.0917. Min Act: -0.0000

Data Index: 1515821 (Python Code)

Max Activating Token Index: 135

Text #16

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.0957. Min Act: -0.0000

Data Index: 1383887 (Python Code)

Max Activating Token Index: 556

Text #17

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.1169. Min Act: -0.0000

Data Index: 1606972 (Python Code)

Max Activating Token Index: 784

Text #18

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.0861. Min Act: -0.0000

Data Index: 1446701 (Python Code)

Max Activating Token Index: 697

Text #19

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.0834. Min Act: -0.0000

Data Index: 1522400 (Python Code)

Max Activating Token Index: 270