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

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

Neuron 2675 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.8210. Min Act: -0.0000

Data Index: 1651300 (Python Code)

Max Activating Token Index: 128

Text #1

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.5606. Min Act: -0.0000

Data Index: 1655559 (Python Code)

Max Activating Token Index: 252

Text #2

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.5568. Min Act: -0.0000

Data Index: 1444558 (Python Code)

Max Activating Token Index: 113

Text #3

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.4141. Min Act: -0.0001

Data Index: 1617517 (Python Code)

Max Activating Token Index: 305

Text #4

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.2464. Min Act: -0.0001

Data Index: 1485603 (Python Code)

Max Activating Token Index: 140

Text #5

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.2414. Min Act: -0.0001

Data Index: 1428022 (Python Code)

Max Activating Token Index: 711

Text #6

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.4467. Min Act: -0.0001

Data Index: 1500443 (Python Code)

Max Activating Token Index: 40

Text #7

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.2635. Min Act: -0.0001

Data Index: 1478578 (Python Code)

Max Activating Token Index: 647

Text #8

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.2916. Min Act: -0.0000

Data Index: 1479312 (Python Code)

Max Activating Token Index: 518

Text #9

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.2099. Min Act: -0.0001

Data Index: 1363991 (Python Code)

Max Activating Token Index: 330

Text #10

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.2439. Min Act: -0.0001

Data Index: 1517464 (Python Code)

Max Activating Token Index: 328

Text #11

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.2170. Min Act: -0.0001

Data Index: 1527392 (Python Code)

Max Activating Token Index: 645

Text #12

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.1651. Min Act: -0.0000

Data Index: 1549995 (Python Code)

Max Activating Token Index: 887

Text #13

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.1426. Min Act: -0.0000

Data Index: 1590508 (Python Code)

Max Activating Token Index: 925

Text #14

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.1388. Min Act: -0.0001

Data Index: 1583674 (Python Code)

Max Activating Token Index: 516

Text #15

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.1960. Min Act: -0.0001

Data Index: 1636158 (Python Code)

Max Activating Token Index: 946

Text #16

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.0926. Min Act: -0.0001

Data Index: 1620500 (Python Code)

Max Activating Token Index: 566

Text #17

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.1614. Min Act: -0.0001

Data Index: 1396101 (Python Code)

Max Activating Token Index: 588

Text #18

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.1213. Min Act: -0.0001

Data Index: 1455063 (Python Code)

Max Activating Token Index: 280

Text #19

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.1131. Min Act: -0.0001

Data Index: 1487801 (Python Code)

Max Activating Token Index: 154