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

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

Neuron 2342 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.9762. Min Act: -0.0000

Data Index: 657722 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.8966. Min Act: -0.0001

Data Index: 1281872 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.9127. Min Act: -0.0000

Data Index: 683628 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.8968. Min Act: -0.0000

Data Index: 146940 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.8161. Min Act: -0.0000

Data Index: 964431 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.8440. Min Act: -0.0000

Data Index: 449918 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.6806. Min Act: -0.0000

Data Index: 902036 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7679. Min Act: -0.0000

Data Index: 1014463 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1359563 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7230. Min Act: -0.0000

Data Index: 658956 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7658. Min Act: -0.0001

Data Index: 680175 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7413. Min Act: -0.0000

Data Index: 18735 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7620. Min Act: -0.0000

Data Index: 833896 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7309. Min Act: -0.0000

Data Index: 1006129 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7222. Min Act: -0.0000

Data Index: 590012 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1108133 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7467. Min Act: -0.0001

Data Index: 707707 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.6954. Min Act: -0.0000

Data Index: 616380 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.6856. Min Act: -0.0000

Data Index: 109056 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.6629. Min Act: -0.0001

Data Index: 109092 (C4 (Web Text))

Max Activating Token Index: 752