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

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

Neuron 2977 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.4697. Min Act: -0.0001

Data Index: 1556756 (Python Code)

Max Activating Token Index: 31

Text #1

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.5091. Min Act: -0.0001

Data Index: 1633157 (Python Code)

Max Activating Token Index: 24

Text #2

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.4311. Min Act: -0.0001

Data Index: 1560794 (Python Code)

Max Activating Token Index: 181

Text #3

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.3369. Min Act: -0.0001

Data Index: 1515098 (Python Code)

Max Activating Token Index: 91

Text #4

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.2419. Min Act: -0.0001

Data Index: 1557983 (Python Code)

Max Activating Token Index: 23

Text #5

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.2529. Min Act: -0.0001

Data Index: 1391216 (Python Code)

Max Activating Token Index: 296

Text #6

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.1474. Min Act: -0.0001

Data Index: 1436551 (Python Code)

Max Activating Token Index: 46

Text #7

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.1441. Min Act: -0.0001

Data Index: 1636885 (Python Code)

Max Activating Token Index: 60

Text #8

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.0951. Min Act: -0.0001

Data Index: 1557936 (Python Code)

Max Activating Token Index: 70

Text #9

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.1406. Min Act: -0.0001

Data Index: 1438045 (Python Code)

Max Activating Token Index: 38

Text #10

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.0967. Min Act: -0.0001

Data Index: 1654419 (Python Code)

Max Activating Token Index: 67

Text #11

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.1279. Min Act: -0.0001

Data Index: 1438123 (Python Code)

Max Activating Token Index: 437

Text #12

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.0961. Min Act: -0.0001

Data Index: 1507120 (Python Code)

Max Activating Token Index: 9

Text #13

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.0913. Min Act: -0.0001

Data Index: 1444381 (Python Code)

Max Activating Token Index: 448

Text #14

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.0871. Min Act: -0.0001

Data Index: 1636471 (Python Code)

Max Activating Token Index: 272

Text #15

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.1251. Min Act: -0.0001

Data Index: 1509179 (Python Code)

Max Activating Token Index: 484

Text #16

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.1183. Min Act: -0.0001

Data Index: 1581541 (Python Code)

Max Activating Token Index: 189

Text #17

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.1168. Min Act: -0.0001

Data Index: 1387733 (Python Code)

Max Activating Token Index: 67

Text #18

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.0759. Min Act: -0.0001

Data Index: 1545992 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.1029. Min Act: -0.0001

Data Index: 1538298 (Python Code)

Max Activating Token Index: 63