Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1400 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4501. Min Act: -0.0003

Data Index: 1372905 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4437. Min Act: -0.0003

Data Index: 1375214 (Python Code)

Max Activating Token Index: 973

Text #2

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4640. Min Act: -0.0003

Data Index: 1384403 (Python Code)

Max Activating Token Index: 858

Text #3

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4538. Min Act: -0.0003

Data Index: 1419632 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4454. Min Act: -0.0003

Data Index: 1545845 (Python Code)

Max Activating Token Index: 42

Text #5

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4000. Min Act: -0.0003

Data Index: 1465432 (Python Code)

Max Activating Token Index: 929

Text #6

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4247. Min Act: -0.0003

Data Index: 1565625 (Python Code)

Max Activating Token Index: 990

Text #7

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4505. Min Act: -0.0003

Data Index: 1577246 (Python Code)

Max Activating Token Index: 922

Text #8

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4078. Min Act: -0.0003

Data Index: 1576784 (Python Code)

Max Activating Token Index: 982

Text #9

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4187. Min Act: -0.0003

Data Index: 1405643 (Python Code)

Max Activating Token Index: 531

Text #10

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4311. Min Act: -0.0003

Data Index: 1490953 (Python Code)

Max Activating Token Index: 310

Text #11

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4307. Min Act: -0.0003

Data Index: 1650312 (Python Code)

Max Activating Token Index: 20

Text #12

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3894. Min Act: -0.0003

Data Index: 1564421 (Python Code)

Max Activating Token Index: 928

Text #13

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4235. Min Act: -0.0003

Data Index: 1471412 (Python Code)

Max Activating Token Index: 949

Text #14

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3740. Min Act: -0.0003

Data Index: 1384552 (Python Code)

Max Activating Token Index: 875

Text #15

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4127. Min Act: -0.0003

Data Index: 1647006 (Python Code)

Max Activating Token Index: 866

Text #16

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4265. Min Act: -0.0003

Data Index: 1590210 (Python Code)

Max Activating Token Index: 25

Text #17

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4164. Min Act: -0.0003

Data Index: 1379638 (Python Code)

Max Activating Token Index: 847

Text #18

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3953. Min Act: -0.0003

Data Index: 1619177 (Python Code)

Max Activating Token Index: 844

Text #19

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4206. Min Act: -0.0003

Data Index: 1566687 (Python Code)

Max Activating Token Index: 873