Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2303 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.5517. Min Act: -0.0003

Data Index: 1163022 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.4643. Min Act: -0.0003

Data Index: 670972 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3995. Min Act: -0.0003

Data Index: 1295658 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.4257. Min Act: -0.0003

Data Index: 1100497 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.4082. Min Act: -0.0003

Data Index: 632798 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3816. Min Act: -0.0003

Data Index: 118208 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.4042. Min Act: -0.0003

Data Index: 392566 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3757. Min Act: -0.0003

Data Index: 924482 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3630. Min Act: -0.0003

Data Index: 777269 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3969. Min Act: -0.0003

Data Index: 22757 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3829. Min Act: -0.0003

Data Index: 1261777 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3811. Min Act: -0.0003

Data Index: 361761 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3811. Min Act: -0.0003

Data Index: 1099455 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3654. Min Act: -0.0003

Data Index: 690851 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3419. Min Act: -0.0003

Data Index: 462540 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3626. Min Act: -0.0003

Data Index: 58363 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3143. Min Act: -0.0003

Data Index: 1046957 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3877. Min Act: -0.0003

Data Index: 734246 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3530. Min Act: -0.0003

Data Index: 718474 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3478. Min Act: -0.0003

Data Index: 135087 (C4 (Web Text))

Max Activating Token Index: 416