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

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

Neuron 804 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: 0.1573. Min Range: -0.1573

Max Act: 0.1573. Min Act: -0.0002

Data Index: 921645 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.0344. Min Act: -0.0002

Data Index: 209828 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1169. Min Act: -0.0002

Data Index: 1312177 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.0900. Min Act: -0.0002

Data Index: 875188 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.0686. Min Act: -0.0002

Data Index: 72385 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.0725. Min Act: -0.0002

Data Index: 290273 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.0636. Min Act: -0.0002

Data Index: 997359 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.0776. Min Act: -0.0001

Data Index: 600357 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.0737. Min Act: -0.0002

Data Index: 807801 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.0877. Min Act: -0.0002

Data Index: 853697 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.0723. Min Act: -0.0002

Data Index: 343925 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.0326. Min Act: -0.0002

Data Index: 156705 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.0677. Min Act: -0.0002

Data Index: 579096 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1327017 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.0429. Min Act: -0.0002

Data Index: 661742 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.0723. Min Act: -0.0002

Data Index: 797428 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.0195. Min Act: -0.0002

Data Index: 637808 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.0614. Min Act: -0.0002

Data Index: 626498 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.0091. Min Act: -0.0002

Data Index: 695966 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1232385 (C4 (Web Text))

Max Activating Token Index: 639