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

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

Neuron 3414 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: 0.5235. Min Range: -0.5235

Max Act: 0.4960. Min Act: -0.0001

Data Index: 6020 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.5235. Min Range: -0.5235

Max Act: 0.5141. Min Act: -0.0002

Data Index: 1158361 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.5235. Min Range: -0.5235

Max Act: 0.4568. Min Act: -0.0001

Data Index: 1128214 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 0.5235. Min Range: -0.5235

Max Act: 0.5235. Min Act: -0.0002

Data Index: 807739 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.5235. Min Range: -0.5235

Max Act: 0.4880. Min Act: -0.0001

Data Index: 1027687 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.5235. Min Range: -0.5235

Max Act: 0.5228. Min Act: -0.0002

Data Index: 389003 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.5235. Min Range: -0.5235

Max Act: 0.4769. Min Act: -0.0001

Data Index: 908520 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.5235. Min Range: -0.5235

Max Act: 0.4635. Min Act: -0.0001

Data Index: 1199917 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.5235. Min Range: -0.5235

Max Act: 0.4876. Min Act: -0.0001

Data Index: 852390 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.5235. Min Range: -0.5235

Max Act: 0.4663. Min Act: -0.0002

Data Index: 488105 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.5235. Min Range: -0.5235

Max Act: 0.4361. Min Act: -0.0002

Data Index: 796872 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.5235. Min Range: -0.5235

Max Act: 0.4891. Min Act: -0.0001

Data Index: 1245416 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.5235. Min Range: -0.5235

Max Act: 0.4744. Min Act: -0.0001

Data Index: 1325285 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 0.5235. Min Range: -0.5235

Max Act: 0.4426. Min Act: -0.0002

Data Index: 7888 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.5235. Min Range: -0.5235

Max Act: 0.4547. Min Act: -0.0001

Data Index: 413513 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.5235. Min Range: -0.5235

Max Act: 0.4388. Min Act: -0.0002

Data Index: 99568 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.5235. Min Range: -0.5235

Max Act: 0.4240. Min Act: -0.0001

Data Index: 38561 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.5235. Min Range: -0.5235

Max Act: 0.4186. Min Act: -0.0001

Data Index: 377213 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.5235. Min Range: -0.5235

Max Act: 0.4426. Min Act: -0.0002

Data Index: 777661 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.5235. Min Range: -0.5235

Max Act: 0.4093. Min Act: -0.0001

Data Index: 1153932 (C4 (Web Text))

Max Activating Token Index: 371