Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1721 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1205. Min Act: -0.0002

Data Index: 1060277 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1145. Min Act: -0.0002

Data Index: 1135456 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1099. Min Act: -0.0002

Data Index: 284364 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1022. Min Act: -0.0002

Data Index: 425502 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1008. Min Act: -0.0002

Data Index: 1145478 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1031. Min Act: -0.0002

Data Index: 392067 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1003. Min Act: -0.0002

Data Index: 942940 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0985. Min Act: -0.0002

Data Index: 1139743 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0999. Min Act: -0.0002

Data Index: 856943 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0985. Min Act: -0.0002

Data Index: 1297049 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0966. Min Act: -0.0002

Data Index: 27132 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0965. Min Act: -0.0002

Data Index: 431336 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0932. Min Act: -0.0002

Data Index: 386623 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0967. Min Act: -0.0002

Data Index: 993279 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0968. Min Act: -0.0002

Data Index: 257525 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0954. Min Act: -0.0002

Data Index: 583109 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0952. Min Act: -0.0002

Data Index: 516844 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0949. Min Act: -0.0002

Data Index: 1280804 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0940. Min Act: -0.0002

Data Index: 242496 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0937. Min Act: -0.0002

Data Index: 566442 (C4 (Web Text))

Max Activating Token Index: 929