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

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

Neuron 3543 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4618. Min Act: -0.0001

Data Index: 1588805 (Python Code)

Max Activating Token Index: 716

Text #1

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4462. Min Act: -0.0001

Data Index: 1368339 (Python Code)

Max Activating Token Index: 171

Text #2

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4056. Min Act: -0.0001

Data Index: 1526779 (Python Code)

Max Activating Token Index: 79

Text #3

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3918. Min Act: -0.0001

Data Index: 1595490 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3970. Min Act: -0.0001

Data Index: 1433156 (Python Code)

Max Activating Token Index: 956

Text #5

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4079. Min Act: -0.0001

Data Index: 1402060 (Python Code)

Max Activating Token Index: 505

Text #6

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4029. Min Act: -0.0001

Data Index: 1430827 (Python Code)

Max Activating Token Index: 983

Text #7

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3619. Min Act: -0.0001

Data Index: 1411698 (Python Code)

Max Activating Token Index: 377

Text #8

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3494. Min Act: -0.0001

Data Index: 1601790 (Python Code)

Max Activating Token Index: 279

Text #9

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3519. Min Act: -0.0001

Data Index: 1624387 (Python Code)

Max Activating Token Index: 189

Text #10

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3842. Min Act: -0.0001

Data Index: 1552574 (Python Code)

Max Activating Token Index: 194

Text #11

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3344. Min Act: -0.0001

Data Index: 1373324 (Python Code)

Max Activating Token Index: 1005

Text #12

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3282. Min Act: -0.0001

Data Index: 1628394 (Python Code)

Max Activating Token Index: 977

Text #13

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3460. Min Act: -0.0001

Data Index: 1379246 (Python Code)

Max Activating Token Index: 1010

Text #14

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3194. Min Act: -0.0001

Data Index: 1608174 (Python Code)

Max Activating Token Index: 726

Text #15

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3252. Min Act: -0.0001

Data Index: 1440823 (Python Code)

Max Activating Token Index: 105

Text #16

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3119. Min Act: -0.0001

Data Index: 1650503 (Python Code)

Max Activating Token Index: 167

Text #17

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3310. Min Act: -0.0001

Data Index: 1536907 (Python Code)

Max Activating Token Index: 342

Text #18

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3468. Min Act: -0.0001

Data Index: 1488586 (Python Code)

Max Activating Token Index: 862

Text #19

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3338. Min Act: -0.0001

Data Index: 1639338 (Python Code)

Max Activating Token Index: 576