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

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

Neuron 4216 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.6031. Min Act: -0.0000

Data Index: 1093708 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.0893. Min Act: -0.0000

Data Index: 1492968 (Python Code)

Max Activating Token Index: 719

Text #2

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.1539. Min Act: -0.0000

Data Index: 1417209 (Python Code)

Max Activating Token Index: 87

Text #3

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.0825. Min Act: -0.0000

Data Index: 255319 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.0976. Min Act: -0.0000

Data Index: 1528601 (Python Code)

Max Activating Token Index: 926

Text #5

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.0515. Min Act: -0.0000

Data Index: 1262420 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 1.6031. Min Range: -1.6031

Max Act: 0.9592. Min Act: -0.0000

Data Index: 1624775 (Python Code)

Max Activating Token Index: 271

Text #7

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.0425. Min Act: -0.0000

Data Index: 1412635 (Python Code)

Max Activating Token Index: 426

Text #8

Max Range: 1.6031. Min Range: -1.6031

Max Act: 0.9675. Min Act: -0.0000

Data Index: 407583 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.0140. Min Act: -0.0000

Data Index: 1549678 (Python Code)

Max Activating Token Index: 987

Text #10

Max Range: 1.6031. Min Range: -1.6031

Max Act: 0.9131. Min Act: -0.0000

Data Index: 1619717 (Python Code)

Max Activating Token Index: 385

Text #11

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.0341. Min Act: -0.0000

Data Index: 1650912 (Python Code)

Max Activating Token Index: 246

Text #12

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.0101. Min Act: -0.0000

Data Index: 1420272 (Python Code)

Max Activating Token Index: 222

Text #13

Max Range: 1.6031. Min Range: -1.6031

Max Act: 0.9502. Min Act: -0.0000

Data Index: 233595 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 1.6031. Min Range: -1.6031

Max Act: 0.9965. Min Act: -0.0000

Data Index: 1155347 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 1.6031. Min Range: -1.6031

Max Act: 0.9871. Min Act: -0.0000

Data Index: 1466501 (Python Code)

Max Activating Token Index: 667

Text #16

Max Range: 1.6031. Min Range: -1.6031

Max Act: 0.9724. Min Act: -0.0000

Data Index: 1397901 (Python Code)

Max Activating Token Index: 858

Text #17

Max Range: 1.6031. Min Range: -1.6031

Max Act: 0.9724. Min Act: -0.0000

Data Index: 1430939 (Python Code)

Max Activating Token Index: 461

Text #18

Max Range: 1.6031. Min Range: -1.6031

Max Act: 0.9300. Min Act: -0.0000

Data Index: 1553276 (Python Code)

Max Activating Token Index: 941

Text #19

Max Range: 1.6031. Min Range: -1.6031

Max Act: 0.9833. Min Act: -0.0000

Data Index: 1624175 (Python Code)

Max Activating Token Index: 946