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

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

Neuron 3711 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.3636. Min Act: -0.0001

Data Index: 1566469 (Python Code)

Max Activating Token Index: 880

Text #1

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.4071. Min Act: -0.0000

Data Index: 1481151 (Python Code)

Max Activating Token Index: 307

Text #2

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.2378. Min Act: -0.0000

Data Index: 1627096 (Python Code)

Max Activating Token Index: 852

Text #3

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.2505. Min Act: -0.0000

Data Index: 1388994 (Python Code)

Max Activating Token Index: 743

Text #4

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.2770. Min Act: -0.0000

Data Index: 1651058 (Python Code)

Max Activating Token Index: 382

Text #5

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.1583. Min Act: -0.0000

Data Index: 1623853 (Python Code)

Max Activating Token Index: 887

Text #6

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.2187. Min Act: -0.0000

Data Index: 1520193 (Python Code)

Max Activating Token Index: 195

Text #7

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.2394. Min Act: -0.0000

Data Index: 1396899 (Python Code)

Max Activating Token Index: 124

Text #8

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.1976. Min Act: -0.0001

Data Index: 1369514 (Python Code)

Max Activating Token Index: 207

Text #9

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.2328. Min Act: -0.0000

Data Index: 1493574 (Python Code)

Max Activating Token Index: 828

Text #10

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.2306. Min Act: -0.0000

Data Index: 1586070 (Python Code)

Max Activating Token Index: 74

Text #11

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.1939. Min Act: -0.0001

Data Index: 1582286 (Python Code)

Max Activating Token Index: 891

Text #12

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.2017. Min Act: -0.0000

Data Index: 1637678 (Python Code)

Max Activating Token Index: 551

Text #13

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.2465. Min Act: -0.0000

Data Index: 1621408 (Python Code)

Max Activating Token Index: 228

Text #14

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.1991. Min Act: -0.0000

Data Index: 1584295 (Python Code)

Max Activating Token Index: 163

Text #15

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.2101. Min Act: -0.0000

Data Index: 1510333 (Python Code)

Max Activating Token Index: 17

Text #16

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.1921. Min Act: -0.0001

Data Index: 1492310 (Python Code)

Max Activating Token Index: 274

Text #17

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.1382. Min Act: -0.0001

Data Index: 1378504 (Python Code)

Max Activating Token Index: 331

Text #18

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.1061. Min Act: -0.0000

Data Index: 1451564 (Python Code)

Max Activating Token Index: 672

Text #19

Max Range: 1.4071. Min Range: -1.4071

Max Act: 1.1291. Min Act: -0.0001

Data Index: 1474545 (Python Code)

Max Activating Token Index: 65