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

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

Neuron 4057 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1630984 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1466195 (Python Code)

Max Activating Token Index: 633

Text #2

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1624825 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1508573 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0378. Min Act: -0.0002

Data Index: 137372 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0295. Min Act: -0.0002

Data Index: 1522961 (Python Code)

Max Activating Token Index: 83

Text #6

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1377544 (Python Code)

Max Activating Token Index: 1013

Text #7

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1567020 (Python Code)

Max Activating Token Index: 150

Text #8

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1551508 (Python Code)

Max Activating Token Index: 647

Text #9

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1412432 (Python Code)

Max Activating Token Index: 212

Text #10

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1246336 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1626656 (Python Code)

Max Activating Token Index: 325

Text #12

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1532390 (Python Code)

Max Activating Token Index: 941

Text #13

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0266. Min Act: -0.0002

Data Index: 35236 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1472991 (Python Code)

Max Activating Token Index: 893

Text #15

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1636216 (Python Code)

Max Activating Token Index: 698

Text #16

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1541091 (Python Code)

Max Activating Token Index: 6

Text #17

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0293. Min Act: -0.0002

Data Index: 552780 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0290. Min Act: -0.0002

Data Index: 27075 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1647615 (Python Code)

Max Activating Token Index: 718