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

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

Neuron 1359 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3484. Min Range: -1.3484

Max Act: 1.3484. Min Act: -0.0001

Data Index: 1497916 (Python Code)

Max Activating Token Index: 857

Text #1

Max Range: 1.3484. Min Range: -1.3484

Max Act: 1.2836. Min Act: -0.0001

Data Index: 1535253 (Python Code)

Max Activating Token Index: 615

Text #2

Max Range: 1.3484. Min Range: -1.3484

Max Act: 1.2471. Min Act: -0.0001

Data Index: 1477773 (Python Code)

Max Activating Token Index: 506

Text #3

Max Range: 1.3484. Min Range: -1.3484

Max Act: 1.2440. Min Act: -0.0001

Data Index: 1619022 (Python Code)

Max Activating Token Index: 657

Text #4

Max Range: 1.3484. Min Range: -1.3484

Max Act: 1.2308. Min Act: -0.0001

Data Index: 1541139 (Python Code)

Max Activating Token Index: 788

Text #5

Max Range: 1.3484. Min Range: -1.3484

Max Act: 1.2140. Min Act: -0.0001

Data Index: 1595521 (Python Code)

Max Activating Token Index: 701

Text #6

Max Range: 1.3484. Min Range: -1.3484

Max Act: 1.0201. Min Act: -0.0001

Data Index: 1380509 (Python Code)

Max Activating Token Index: 267

Text #7

Max Range: 1.3484. Min Range: -1.3484

Max Act: 1.0278. Min Act: -0.0001

Data Index: 1451224 (Python Code)

Max Activating Token Index: 307

Text #8

Max Range: 1.3484. Min Range: -1.3484

Max Act: 1.0175. Min Act: -0.0001

Data Index: 1597181 (Python Code)

Max Activating Token Index: 254

Text #9

Max Range: 1.3484. Min Range: -1.3484

Max Act: 0.9884. Min Act: -0.0001

Data Index: 1432687 (Python Code)

Max Activating Token Index: 838

Text #10

Max Range: 1.3484. Min Range: -1.3484

Max Act: 0.9822. Min Act: -0.0001

Data Index: 1541132 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 1.3484. Min Range: -1.3484

Max Act: 0.9623. Min Act: -0.0001

Data Index: 1484327 (Python Code)

Max Activating Token Index: 175

Text #12

Max Range: 1.3484. Min Range: -1.3484

Max Act: 0.9793. Min Act: -0.0001

Data Index: 1447815 (Python Code)

Max Activating Token Index: 700

Text #13

Max Range: 1.3484. Min Range: -1.3484

Max Act: 0.9141. Min Act: -0.0001

Data Index: 1515350 (Python Code)

Max Activating Token Index: 92

Text #14

Max Range: 1.3484. Min Range: -1.3484

Max Act: 0.9366. Min Act: -0.0001

Data Index: 1394691 (Python Code)

Max Activating Token Index: 803

Text #15

Max Range: 1.3484. Min Range: -1.3484

Max Act: 0.9630. Min Act: -0.0001

Data Index: 1644032 (Python Code)

Max Activating Token Index: 901

Text #16

Max Range: 1.3484. Min Range: -1.3484

Max Act: 0.8954. Min Act: -0.0001

Data Index: 1617706 (Python Code)

Max Activating Token Index: 298

Text #17

Max Range: 1.3484. Min Range: -1.3484

Max Act: 0.8815. Min Act: -0.0001

Data Index: 1370167 (Python Code)

Max Activating Token Index: 815

Text #18

Max Range: 1.3484. Min Range: -1.3484

Max Act: 0.8843. Min Act: -0.0001

Data Index: 1635357 (Python Code)

Max Activating Token Index: 261

Text #19

Max Range: 1.3484. Min Range: -1.3484

Max Act: 0.9065. Min Act: -0.0001

Data Index: 1404948 (Python Code)

Max Activating Token Index: 675