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

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

Neuron 3656 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: 0.7873. Min Range: -0.7873

Max Act: 0.7873. Min Act: -0.0001

Data Index: 1644057 (Python Code)

Max Activating Token Index: 124

Text #1

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.7224. Min Act: -0.0001

Data Index: 1389671 (Python Code)

Max Activating Token Index: 762

Text #2

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.6941. Min Act: -0.0001

Data Index: 1597053 (Python Code)

Max Activating Token Index: 35

Text #3

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.6530. Min Act: -0.0001

Data Index: 1444447 (Python Code)

Max Activating Token Index: 21

Text #4

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.6252. Min Act: -0.0001

Data Index: 1647711 (Python Code)

Max Activating Token Index: 145

Text #5

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.6397. Min Act: -0.0001

Data Index: 1425668 (Python Code)

Max Activating Token Index: 29

Text #6

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.6246. Min Act: -0.0001

Data Index: 1571919 (Python Code)

Max Activating Token Index: 22

Text #7

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.6221. Min Act: -0.0001

Data Index: 536757 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.6112. Min Act: -0.0001

Data Index: 1337172 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.6089. Min Act: -0.0001

Data Index: 1360976 (Python Code)

Max Activating Token Index: 64

Text #10

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.6023. Min Act: -0.0001

Data Index: 1614206 (Python Code)

Max Activating Token Index: 330

Text #11

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.6031. Min Act: -0.0001

Data Index: 1416350 (Python Code)

Max Activating Token Index: 643

Text #12

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.6096. Min Act: -0.0001

Data Index: 239467 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.5774. Min Act: -0.0001

Data Index: 1393059 (Python Code)

Max Activating Token Index: 91

Text #14

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.5447. Min Act: -0.0001

Data Index: 1474453 (Python Code)

Max Activating Token Index: 523

Text #15

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.5763. Min Act: -0.0001

Data Index: 1588188 (Python Code)

Max Activating Token Index: 862

Text #16

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.5690. Min Act: -0.0001

Data Index: 1488228 (Python Code)

Max Activating Token Index: 214

Text #17

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.5613. Min Act: -0.0001

Data Index: 1366311 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.5771. Min Act: -0.0001

Data Index: 1559702 (Python Code)

Max Activating Token Index: 784

Text #19

Max Range: 0.7873. Min Range: -0.7873

Max Act: 0.5590. Min Act: -0.0001

Data Index: 1581583 (Python Code)

Max Activating Token Index: 53