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

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

Neuron 1415 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.3911. Min Act: -0.0000

Data Index: 1387731 (Python Code)

Max Activating Token Index: 178

Text #1

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.3010. Min Act: -0.0000

Data Index: 1594307 (Python Code)

Max Activating Token Index: 71

Text #2

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.2851. Min Act: 0.0001

Data Index: 1575006 (Python Code)

Max Activating Token Index: 267

Text #3

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.2486. Min Act: -0.0000

Data Index: 1363002 (Python Code)

Max Activating Token Index: 853

Text #4

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.2236. Min Act: 0.0001

Data Index: 1367779 (Python Code)

Max Activating Token Index: 543

Text #5

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1820. Min Act: 0.0001

Data Index: 1481138 (Python Code)

Max Activating Token Index: 84

Text #6

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.2273. Min Act: -0.0000

Data Index: 1640457 (Python Code)

Max Activating Token Index: 1020

Text #7

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1673. Min Act: 0.0001

Data Index: 1419988 (Python Code)

Max Activating Token Index: 877

Text #8

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1312. Min Act: -0.0000

Data Index: 1647960 (Python Code)

Max Activating Token Index: 639

Text #9

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1147. Min Act: -0.0000

Data Index: 1621058 (Python Code)

Max Activating Token Index: 726

Text #10

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1099. Min Act: 0.0000

Data Index: 1403950 (Python Code)

Max Activating Token Index: 458

Text #11

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1391. Min Act: 0.0001

Data Index: 1412709 (Python Code)

Max Activating Token Index: 397

Text #12

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1571. Min Act: -0.0000

Data Index: 1414438 (Python Code)

Max Activating Token Index: 659

Text #13

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1147. Min Act: 0.0000

Data Index: 1470929 (Python Code)

Max Activating Token Index: 257

Text #14

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1798. Min Act: -0.0000

Data Index: 1566782 (Python Code)

Max Activating Token Index: 297

Text #15

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1105. Min Act: 0.0001

Data Index: 1454994 (Python Code)

Max Activating Token Index: 244

Text #16

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.0734. Min Act: -0.0000

Data Index: 1595526 (Python Code)

Max Activating Token Index: 544

Text #17

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1399398 (Python Code)

Max Activating Token Index: 268

Text #18

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1061. Min Act: 0.0001

Data Index: 1459911 (Python Code)

Max Activating Token Index: 908

Text #19

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1364704 (Python Code)

Max Activating Token Index: 828