Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2024 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3582. Min Act: -0.0002

Data Index: 796204 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3923. Min Act: -0.0002

Data Index: 981383 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3970. Min Act: -0.0002

Data Index: 554211 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3674. Min Act: -0.0002

Data Index: 1263497 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3845. Min Act: -0.0002

Data Index: 368046 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3436. Min Act: -0.0002

Data Index: 142454 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3649. Min Act: -0.0002

Data Index: 462857 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3633. Min Act: -0.0002

Data Index: 31175 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3761. Min Act: -0.0002

Data Index: 783417 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3706. Min Act: -0.0002

Data Index: 91389 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3654. Min Act: -0.0002

Data Index: 805393 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.4068. Min Act: -0.0002

Data Index: 1207904 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3777. Min Act: -0.0002

Data Index: 546054 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3643. Min Act: -0.0002

Data Index: 813680 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3612. Min Act: -0.0002

Data Index: 23148 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3580. Min Act: -0.0002

Data Index: 966132 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3480. Min Act: -0.0002

Data Index: 792330 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3448. Min Act: -0.0002

Data Index: 858482 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3415. Min Act: -0.0002

Data Index: 1080360 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3214. Min Act: -0.0002

Data Index: 910227 (C4 (Web Text))

Max Activating Token Index: 384