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

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

Neuron 2455 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.2297. Min Act: -0.0000

Data Index: 1075691 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.1207. Min Act: -0.0000

Data Index: 248918 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.2120. Min Act: -0.0000

Data Index: 1197014 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.1127. Min Act: -0.0000

Data Index: 35932 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.0694. Min Act: -0.0000

Data Index: 659853 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.9887. Min Act: -0.0001

Data Index: 280710 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.9159. Min Act: -0.0000

Data Index: 1299101 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.9867. Min Act: -0.0000

Data Index: 1145217 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.0215. Min Act: -0.0000

Data Index: 571848 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1191812 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.8828. Min Act: -0.0000

Data Index: 207332 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.8730. Min Act: -0.0000

Data Index: 42266 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.8761. Min Act: -0.0000

Data Index: 1292187 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.8651. Min Act: -0.0000

Data Index: 1058427 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.8769. Min Act: -0.0000

Data Index: 476451 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.8908. Min Act: -0.0000

Data Index: 67444 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.8515. Min Act: -0.0000

Data Index: 249310 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.8409. Min Act: -0.0000

Data Index: 173301 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.8598. Min Act: -0.0000

Data Index: 931155 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7873. Min Act: -0.0000

Data Index: 462474 (C4 (Web Text))

Max Activating Token Index: 182