Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2593 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.8845. Min Act: -0.0002

Data Index: 1071484 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.7975. Min Act: -0.0002

Data Index: 91288 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.7085. Min Act: -0.0002

Data Index: 1014567 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.7787. Min Act: -0.0001

Data Index: 485111 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.6867. Min Act: -0.0002

Data Index: 378415 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.7421. Min Act: -0.0002

Data Index: 761422 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.7009. Min Act: -0.0002

Data Index: 622841 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.6155. Min Act: -0.0002

Data Index: 266506 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.6162. Min Act: -0.0002

Data Index: 1239261 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.6538. Min Act: -0.0002

Data Index: 98846 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.6443. Min Act: -0.0002

Data Index: 1211493 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.5646. Min Act: -0.0002

Data Index: 467872 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.6701. Min Act: -0.0002

Data Index: 225985 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.6652. Min Act: -0.0002

Data Index: 704426 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.7236. Min Act: -0.0002

Data Index: 509942 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.5894. Min Act: -0.0002

Data Index: 660340 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.7225. Min Act: -0.0002

Data Index: 1206826 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.5508. Min Act: -0.0002

Data Index: 24987 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.6006. Min Act: -0.0002

Data Index: 949295 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.5422. Min Act: -0.0001

Data Index: 1092661 (C4 (Web Text))

Max Activating Token Index: 985