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

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

Neuron 3609 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.4208. Min Act: -0.0000

Data Index: 556366 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3889. Min Act: -0.0000

Data Index: 1452337 (Python Code)

Max Activating Token Index: 758

Text #2

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3739. Min Act: -0.0000

Data Index: 1569349 (Python Code)

Max Activating Token Index: 194

Text #3

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3841. Min Act: -0.0000

Data Index: 1426535 (Python Code)

Max Activating Token Index: 230

Text #4

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3553. Min Act: -0.0000

Data Index: 1524413 (Python Code)

Max Activating Token Index: 930

Text #5

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1469994 (Python Code)

Max Activating Token Index: 673

Text #6

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3451. Min Act: -0.0000

Data Index: 256123 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3679. Min Act: -0.0000

Data Index: 1380835 (Python Code)

Max Activating Token Index: 114

Text #8

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3504. Min Act: -0.0000

Data Index: 1491795 (Python Code)

Max Activating Token Index: 90

Text #9

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1620255 (Python Code)

Max Activating Token Index: 161

Text #10

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3456. Min Act: -0.0000

Data Index: 1593591 (Python Code)

Max Activating Token Index: 649

Text #11

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3492. Min Act: -0.0000

Data Index: 748719 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1389617 (Python Code)

Max Activating Token Index: 246

Text #13

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3265. Min Act: -0.0000

Data Index: 643176 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1539375 (Python Code)

Max Activating Token Index: 221

Text #15

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3248. Min Act: -0.0000

Data Index: 1343759 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1588926 (Python Code)

Max Activating Token Index: 669

Text #17

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1092779 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3179. Min Act: -0.0000

Data Index: 1608814 (Python Code)

Max Activating Token Index: 197

Text #19

Max Range: 0.4208. Min Range: -0.4208

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1521642 (Python Code)

Max Activating Token Index: 166