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

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

Neuron 3293 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: 1.0310. Min Range: -1.0310

Max Act: 0.9733. Min Act: -0.0000

Data Index: 1645157 (Python Code)

Max Activating Token Index: 443

Text #1

Max Range: 1.0310. Min Range: -1.0310

Max Act: 1.0225. Min Act: -0.0000

Data Index: 778353 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 1.0310. Min Range: -1.0310

Max Act: 1.0044. Min Act: -0.0000

Data Index: 1147948 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 1.0310. Min Range: -1.0310

Max Act: 1.0310. Min Act: -0.0000

Data Index: 1380034 (Python Code)

Max Activating Token Index: 419

Text #4

Max Range: 1.0310. Min Range: -1.0310

Max Act: 0.9596. Min Act: -0.0000

Data Index: 1442563 (Python Code)

Max Activating Token Index: 399

Text #5

Max Range: 1.0310. Min Range: -1.0310

Max Act: 0.9085. Min Act: -0.0000

Data Index: 441797 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 1.0310. Min Range: -1.0310

Max Act: 0.9566. Min Act: -0.0000

Data Index: 1588548 (Python Code)

Max Activating Token Index: 925

Text #7

Max Range: 1.0310. Min Range: -1.0310

Max Act: 0.8903. Min Act: -0.0000

Data Index: 890902 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 1.0310. Min Range: -1.0310

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1645287 (Python Code)

Max Activating Token Index: 289

Text #9

Max Range: 1.0310. Min Range: -1.0310

Max Act: 0.9128. Min Act: -0.0000

Data Index: 1011946 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 1.0310. Min Range: -1.0310

Max Act: 0.9717. Min Act: -0.0000

Data Index: 1308598 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 1.0310. Min Range: -1.0310

Max Act: 0.9118. Min Act: -0.0000

Data Index: 43320 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 1.0310. Min Range: -1.0310

Max Act: 0.9167. Min Act: -0.0000

Data Index: 322877 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 1.0310. Min Range: -1.0310

Max Act: 0.8449. Min Act: -0.0000

Data Index: 873151 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 1.0310. Min Range: -1.0310

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1092424 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 1.0310. Min Range: -1.0310

Max Act: 0.8814. Min Act: -0.0000

Data Index: 148382 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 1.0310. Min Range: -1.0310

Max Act: 0.8158. Min Act: -0.0000

Data Index: 778011 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 1.0310. Min Range: -1.0310

Max Act: 0.7789. Min Act: -0.0000

Data Index: 1296395 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 1.0310. Min Range: -1.0310

Max Act: 0.7713. Min Act: -0.0000

Data Index: 247007 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 1.0310. Min Range: -1.0310

Max Act: 0.8130. Min Act: -0.0000

Data Index: 872475 (C4 (Web Text))

Max Activating Token Index: 441