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

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

Neuron 3720 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: 0.2333. Min Range: -0.2333

Max Act: 0.2333. Min Act: -0.0000

Data Index: 1004468 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2122. Min Act: -0.0000

Data Index: 390488 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2110. Min Act: -0.0000

Data Index: 1230586 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2021. Min Act: -0.0000

Data Index: 45331 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1815. Min Act: -0.0000

Data Index: 246577 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1870. Min Act: -0.0000

Data Index: 281971 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1930. Min Act: -0.0000

Data Index: 839007 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1874. Min Act: -0.0000

Data Index: 454260 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1938. Min Act: 0.0000

Data Index: 828772 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1776. Min Act: -0.0000

Data Index: 1306735 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1811. Min Act: -0.0000

Data Index: 529608 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1804. Min Act: -0.0000

Data Index: 831971 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1736. Min Act: -0.0000

Data Index: 205577 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1681. Min Act: -0.0000

Data Index: 485999 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1788. Min Act: -0.0000

Data Index: 1074603 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1912. Min Act: -0.0000

Data Index: 473457 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1672. Min Act: -0.0000

Data Index: 561685 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1778. Min Act: -0.0000

Data Index: 651426 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1692. Min Act: -0.0000

Data Index: 154411 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1702. Min Act: -0.0000

Data Index: 969286 (C4 (Web Text))

Max Activating Token Index: 770