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

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

Neuron 1737 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6379. Min Range: -3.6379

Max Act: 3.6379. Min Act: -0.0002

Data Index: 699443 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 3.6379. Min Range: -3.6379

Max Act: 3.4445. Min Act: -0.0002

Data Index: 813544 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 3.6379. Min Range: -3.6379

Max Act: 3.1284. Min Act: -0.0002

Data Index: 604897 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 3.6379. Min Range: -3.6379

Max Act: 2.8344. Min Act: -0.0002

Data Index: 913598 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 3.6379. Min Range: -3.6379

Max Act: 2.7481. Min Act: -0.0002

Data Index: 60989 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 3.6379. Min Range: -3.6379

Max Act: 2.7371. Min Act: -0.0002

Data Index: 757528 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 3.6379. Min Range: -3.6379

Max Act: 2.7093. Min Act: -0.0002

Data Index: 129298 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 3.6379. Min Range: -3.6379

Max Act: 2.5088. Min Act: -0.0002

Data Index: 1118269 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 3.6379. Min Range: -3.6379

Max Act: 2.5602. Min Act: -0.0002

Data Index: 753859 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 3.6379. Min Range: -3.6379

Max Act: 2.5063. Min Act: -0.0002

Data Index: 669937 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 3.6379. Min Range: -3.6379

Max Act: 2.5336. Min Act: -0.0002

Data Index: 130278 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 3.6379. Min Range: -3.6379

Max Act: 2.4733. Min Act: -0.0002

Data Index: 663614 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 3.6379. Min Range: -3.6379

Max Act: 2.2941. Min Act: -0.0002

Data Index: 1078832 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 3.6379. Min Range: -3.6379

Max Act: 2.5406. Min Act: -0.0002

Data Index: 1055133 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 3.6379. Min Range: -3.6379

Max Act: 2.1925. Min Act: -0.0002

Data Index: 614125 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 3.6379. Min Range: -3.6379

Max Act: 2.2376. Min Act: -0.0002

Data Index: 1309163 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 3.6379. Min Range: -3.6379

Max Act: 2.3257. Min Act: -0.0002

Data Index: 1312434 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 3.6379. Min Range: -3.6379

Max Act: 2.7549. Min Act: -0.0002

Data Index: 1149418 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 3.6379. Min Range: -3.6379

Max Act: 2.2259. Min Act: -0.0002

Data Index: 164683 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 3.6379. Min Range: -3.6379

Max Act: 2.3702. Min Act: -0.0002

Data Index: 1013965 (C4 (Web Text))

Max Activating Token Index: 214