Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1261 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1399. Min Act: -0.0002

Data Index: 1432831 (Python Code)

Max Activating Token Index: 443

Text #1

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1165. Min Act: -0.0002

Data Index: 1542975 (Python Code)

Max Activating Token Index: 909

Text #2

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1148. Min Act: -0.0002

Data Index: 1373749 (Python Code)

Max Activating Token Index: 341

Text #3

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1179. Min Act: -0.0002

Data Index: 1490813 (Python Code)

Max Activating Token Index: 526

Text #4

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1126. Min Act: -0.0002

Data Index: 1490448 (Python Code)

Max Activating Token Index: 588

Text #5

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1031. Min Act: -0.0002

Data Index: 1622272 (Python Code)

Max Activating Token Index: 381

Text #6

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1029. Min Act: -0.0002

Data Index: 1590350 (Python Code)

Max Activating Token Index: 234

Text #7

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0979. Min Act: -0.0002

Data Index: 1399067 (Python Code)

Max Activating Token Index: 504

Text #8

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0961. Min Act: -0.0002

Data Index: 1563531 (Python Code)

Max Activating Token Index: 927

Text #9

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0979. Min Act: -0.0002

Data Index: 1382314 (Python Code)

Max Activating Token Index: 260

Text #10

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1601159 (Python Code)

Max Activating Token Index: 438

Text #11

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0994. Min Act: -0.0002

Data Index: 1532437 (Python Code)

Max Activating Token Index: 150

Text #12

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0976. Min Act: -0.0002

Data Index: 1612709 (Python Code)

Max Activating Token Index: 770

Text #13

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1001. Min Act: -0.0002

Data Index: 1412759 (Python Code)

Max Activating Token Index: 909

Text #14

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0928. Min Act: -0.0002

Data Index: 1656810 (Python Code)

Max Activating Token Index: 751

Text #15

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0917. Min Act: -0.0002

Data Index: 1602171 (Python Code)

Max Activating Token Index: 423

Text #16

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0925. Min Act: -0.0002

Data Index: 1448042 (Python Code)

Max Activating Token Index: 190

Text #17

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1411282 (Python Code)

Max Activating Token Index: 829

Text #18

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0939. Min Act: -0.0002

Data Index: 614262 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0832. Min Act: -0.0002

Data Index: 1430560 (Python Code)

Max Activating Token Index: 1009