Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4355 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.5422. Min Range: -4.5422

Max Act: 4.5422. Min Act: -0.0000

Data Index: 1578603 (Python Code)

Max Activating Token Index: 383

Text #1

Max Range: 4.5422. Min Range: -4.5422

Max Act: 3.3200. Min Act: -0.0000

Data Index: 1419495 (Python Code)

Max Activating Token Index: 245

Text #2

Max Range: 4.5422. Min Range: -4.5422

Max Act: 3.9891. Min Act: -0.0000

Data Index: 1378651 (Python Code)

Max Activating Token Index: 26

Text #3

Max Range: 4.5422. Min Range: -4.5422

Max Act: 3.9652. Min Act: -0.0000

Data Index: 1470122 (Python Code)

Max Activating Token Index: 377

Text #4

Max Range: 4.5422. Min Range: -4.5422

Max Act: 3.1872. Min Act: -0.0000

Data Index: 1455174 (Python Code)

Max Activating Token Index: 815

Text #5

Max Range: 4.5422. Min Range: -4.5422

Max Act: 3.7491. Min Act: -0.0000

Data Index: 1390946 (Python Code)

Max Activating Token Index: 12

Text #6

Max Range: 4.5422. Min Range: -4.5422

Max Act: 3.8114. Min Act: -0.0000

Data Index: 1464134 (Python Code)

Max Activating Token Index: 149

Text #7

Max Range: 4.5422. Min Range: -4.5422

Max Act: 3.6966. Min Act: -0.0000

Data Index: 1418844 (Python Code)

Max Activating Token Index: 178

Text #8

Max Range: 4.5422. Min Range: -4.5422

Max Act: 3.6758. Min Act: -0.0000

Data Index: 1476053 (Python Code)

Max Activating Token Index: 866

Text #9

Max Range: 4.5422. Min Range: -4.5422

Max Act: 3.2207. Min Act: -0.0000

Data Index: 1436331 (Python Code)

Max Activating Token Index: 751

Text #10

Max Range: 4.5422. Min Range: -4.5422

Max Act: 3.3343. Min Act: -0.0000

Data Index: 1653959 (Python Code)

Max Activating Token Index: 926

Text #11

Max Range: 4.5422. Min Range: -4.5422

Max Act: 3.1482. Min Act: -0.0000

Data Index: 1373378 (Python Code)

Max Activating Token Index: 1007

Text #12

Max Range: 4.5422. Min Range: -4.5422

Max Act: 3.2745. Min Act: -0.0000

Data Index: 1381861 (Python Code)

Max Activating Token Index: 918

Text #13

Max Range: 4.5422. Min Range: -4.5422

Max Act: 3.3289. Min Act: -0.0000

Data Index: 1649618 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 4.5422. Min Range: -4.5422

Max Act: 3.0540. Min Act: -0.0000

Data Index: 1459611 (Python Code)

Max Activating Token Index: 697

Text #15

Max Range: 4.5422. Min Range: -4.5422

Max Act: 3.1617. Min Act: -0.0000

Data Index: 1589315 (Python Code)

Max Activating Token Index: 410

Text #16

Max Range: 4.5422. Min Range: -4.5422

Max Act: 3.1406. Min Act: -0.0000

Data Index: 1564436 (Python Code)

Max Activating Token Index: 835

Text #17

Max Range: 4.5422. Min Range: -4.5422

Max Act: 3.4148. Min Act: -0.0000

Data Index: 1570953 (Python Code)

Max Activating Token Index: 960

Text #18

Max Range: 4.5422. Min Range: -4.5422

Max Act: 3.1024. Min Act: -0.0000

Data Index: 1527873 (Python Code)

Max Activating Token Index: 474

Text #19

Max Range: 4.5422. Min Range: -4.5422

Max Act: 3.2016. Min Act: -0.0000

Data Index: 1390387 (Python Code)

Max Activating Token Index: 993