Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 424 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.9189. Min Act: -0.0000

Data Index: 1475422 (Python Code)

Max Activating Token Index: 566

Text #1

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.8644. Min Act: -0.0000

Data Index: 1478619 (Python Code)

Max Activating Token Index: 125

Text #2

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.6245. Min Act: 0.0000

Data Index: 1372657 (Python Code)

Max Activating Token Index: 939

Text #3

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.6654. Min Act: -0.0000

Data Index: 1508260 (Python Code)

Max Activating Token Index: 811

Text #4

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.5637. Min Act: -0.0000

Data Index: 1428777 (Python Code)

Max Activating Token Index: 276

Text #5

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.3775. Min Act: -0.0000

Data Index: 1506051 (Python Code)

Max Activating Token Index: 188

Text #6

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.3986. Min Act: 0.0002

Data Index: 1509617 (Python Code)

Max Activating Token Index: 41

Text #7

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.2957. Min Act: -0.0000

Data Index: 1654579 (Python Code)

Max Activating Token Index: 332

Text #8

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.3210. Min Act: -0.0000

Data Index: 1492721 (Python Code)

Max Activating Token Index: 363

Text #9

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.2421. Min Act: -0.0000

Data Index: 1631786 (Python Code)

Max Activating Token Index: 262

Text #10

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.3044. Min Act: -0.0000

Data Index: 1591904 (Python Code)

Max Activating Token Index: 207

Text #11

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.1817. Min Act: -0.0001

Data Index: 1462134 (Python Code)

Max Activating Token Index: 1003

Text #12

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.1627. Min Act: 0.0001

Data Index: 1475588 (Python Code)

Max Activating Token Index: 362

Text #13

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.1876. Min Act: -0.0001

Data Index: 1468569 (Python Code)

Max Activating Token Index: 80

Text #14

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.1764. Min Act: -0.0000

Data Index: 1366612 (Python Code)

Max Activating Token Index: 505

Text #15

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.2146. Min Act: -0.0001

Data Index: 1645041 (Python Code)

Max Activating Token Index: 678

Text #16

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.1817. Min Act: 0.0001

Data Index: 1529877 (Python Code)

Max Activating Token Index: 300

Text #17

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.1700. Min Act: -0.0000

Data Index: 1379486 (Python Code)

Max Activating Token Index: 365

Text #18

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.1203. Min Act: 0.0001

Data Index: 1543785 (Python Code)

Max Activating Token Index: 142

Text #19

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.2045. Min Act: -0.0000

Data Index: 1382635 (Python Code)

Max Activating Token Index: 71