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

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

Neuron 2636 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.7789. Min Act: -0.0001

Data Index: 1597737 (Python Code)

Max Activating Token Index: 435

Text #1

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.7393. Min Act: -0.0001

Data Index: 1483005 (Python Code)

Max Activating Token Index: 142

Text #2

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.7131. Min Act: -0.0001

Data Index: 1394761 (Python Code)

Max Activating Token Index: 924

Text #3

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.6963. Min Act: -0.0001

Data Index: 1555339 (Python Code)

Max Activating Token Index: 192

Text #4

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.6702. Min Act: -0.0001

Data Index: 1394166 (Python Code)

Max Activating Token Index: 150

Text #5

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.6478. Min Act: -0.0001

Data Index: 1480136 (Python Code)

Max Activating Token Index: 102

Text #6

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.6669. Min Act: -0.0001

Data Index: 1484233 (Python Code)

Max Activating Token Index: 443

Text #7

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.6655. Min Act: -0.0001

Data Index: 1602979 (Python Code)

Max Activating Token Index: 377

Text #8

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.6799. Min Act: -0.0001

Data Index: 1640078 (Python Code)

Max Activating Token Index: 686

Text #9

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.6364. Min Act: -0.0001

Data Index: 1368401 (Python Code)

Max Activating Token Index: 803

Text #10

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.6539. Min Act: -0.0001

Data Index: 1549902 (Python Code)

Max Activating Token Index: 738

Text #11

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.6665. Min Act: -0.0001

Data Index: 1550238 (Python Code)

Max Activating Token Index: 930

Text #12

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.6475. Min Act: -0.0001

Data Index: 1596724 (Python Code)

Max Activating Token Index: 28

Text #13

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.6198. Min Act: -0.0001

Data Index: 1469176 (Python Code)

Max Activating Token Index: 117

Text #14

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.6350. Min Act: -0.0001

Data Index: 1429221 (Python Code)

Max Activating Token Index: 212

Text #15

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.6287. Min Act: -0.0001

Data Index: 1652974 (Python Code)

Max Activating Token Index: 569

Text #16

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.6305. Min Act: -0.0001

Data Index: 1654059 (Python Code)

Max Activating Token Index: 460

Text #17

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.6195. Min Act: -0.0001

Data Index: 1403000 (Python Code)

Max Activating Token Index: 191

Text #18

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.6190. Min Act: -0.0001

Data Index: 1646303 (Python Code)

Max Activating Token Index: 808

Text #19

Max Range: 0.7789. Min Range: -0.7789

Max Act: 0.6554. Min Act: -0.0001

Data Index: 1376022 (Python Code)

Max Activating Token Index: 868