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

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

Neuron 1713 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: 1.1721. Min Range: -1.1721

Max Act: 1.1721. Min Act: -0.0001

Data Index: 149965 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.0826. Min Act: -0.0001

Data Index: 1161367 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.0366. Min Act: -0.0001

Data Index: 1054539 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.9744. Min Act: -0.0001

Data Index: 799257 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8911. Min Act: -0.0002

Data Index: 382816 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.9609. Min Act: -0.0002

Data Index: 953112 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.0299. Min Act: -0.0001

Data Index: 1010533 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.9437. Min Act: -0.0002

Data Index: 1063300 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.9158. Min Act: -0.0001

Data Index: 308798 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8898. Min Act: -0.0002

Data Index: 1163085 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8643. Min Act: -0.0002

Data Index: 1024065 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8837. Min Act: -0.0002

Data Index: 1108562 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8958. Min Act: -0.0002

Data Index: 1236593 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8830. Min Act: -0.0002

Data Index: 181914 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8580. Min Act: -0.0002

Data Index: 686893 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8423. Min Act: -0.0002

Data Index: 607046 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8493. Min Act: -0.0002

Data Index: 1183423 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8537. Min Act: -0.0001

Data Index: 158334 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8080. Min Act: -0.0001

Data Index: 1047523 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8996. Min Act: -0.0002

Data Index: 491158 (C4 (Web Text))

Max Activating Token Index: 793