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

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

Neuron 3388 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.9596. Min Act: -0.0001

Data Index: 200665 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.4006. Min Act: -0.0001

Data Index: 516483 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.5558. Min Act: -0.0001

Data Index: 165975 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.3487. Min Act: -0.0001

Data Index: 337494 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.4485. Min Act: -0.0001

Data Index: 575587 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.3945. Min Act: -0.0001

Data Index: 57317 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.3754. Min Act: -0.0001

Data Index: 689022 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.2337. Min Act: -0.0001

Data Index: 717047 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.0609. Min Act: -0.0001

Data Index: 635893 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.1769. Min Act: -0.0001

Data Index: 688919 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.1701. Min Act: -0.0001

Data Index: 897635 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.2760. Min Act: -0.0001

Data Index: 166891 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.0920. Min Act: -0.0001

Data Index: 313657 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.0800. Min Act: -0.0001

Data Index: 1343810 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.2263. Min Act: -0.0001

Data Index: 716055 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.0744. Min Act: -0.0001

Data Index: 252230 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.1667. Min Act: -0.0001

Data Index: 916513 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 3.9596. Min Range: -3.9596

Max Act: 2.8779. Min Act: -0.0001

Data Index: 647317 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 3.9596. Min Range: -3.9596

Max Act: 2.8710. Min Act: -0.0001

Data Index: 42955 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 3.9596. Min Range: -3.9596

Max Act: 2.9340. Min Act: -0.0001

Data Index: 779926 (C4 (Web Text))

Max Activating Token Index: 296