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

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

Neuron 1641 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.8720. Min Act: -0.0000

Data Index: 204364 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.8977. Min Act: -0.0000

Data Index: 832183 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.8546. Min Act: -0.0000

Data Index: 1091838 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.8021. Min Act: -0.0000

Data Index: 624994 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.7792. Min Act: -0.0000

Data Index: 957902 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.8082. Min Act: -0.0000

Data Index: 286879 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.7835. Min Act: -0.0000

Data Index: 323316 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.7988. Min Act: -0.0000

Data Index: 900624 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.7914. Min Act: -0.0000

Data Index: 385448 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1076162 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.7914. Min Act: -0.0000

Data Index: 1357250 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.7171. Min Act: -0.0000

Data Index: 912131 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1272101 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.7655. Min Act: -0.0000

Data Index: 1334467 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.7196. Min Act: -0.0000

Data Index: 918481 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.7592. Min Act: -0.0000

Data Index: 553877 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.6945. Min Act: -0.0000

Data Index: 971912 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.7274. Min Act: -0.0000

Data Index: 37608 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.7221. Min Act: -0.0000

Data Index: 36471 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.7152. Min Act: -0.0000

Data Index: 1327268 (C4 (Web Text))

Max Activating Token Index: 304