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

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

Neuron 4649 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.5575. Min Act: -0.0000

Data Index: 397232 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.4796. Min Act: -0.0001

Data Index: 119557 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.4668. Min Act: -0.0000

Data Index: 162308 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.4470. Min Act: -0.0000

Data Index: 1184573 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1449309 (Python Code)

Max Activating Token Index: 752

Text #5

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1368290 (Python Code)

Max Activating Token Index: 78

Text #6

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1080649 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.4333. Min Act: -0.0000

Data Index: 954436 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.3707. Min Act: -0.0001

Data Index: 769311 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.3862. Min Act: -0.0000

Data Index: 507138 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.3937. Min Act: -0.0000

Data Index: 181278 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.4020. Min Act: -0.0000

Data Index: 12797 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.3662. Min Act: -0.0000

Data Index: 500944 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.3419. Min Act: -0.0000

Data Index: 447879 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.3630. Min Act: -0.0000

Data Index: 1422815 (Python Code)

Max Activating Token Index: 735

Text #15

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1328948 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.3360. Min Act: -0.0000

Data Index: 704336 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.3015. Min Act: -0.0000

Data Index: 165538 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.3150. Min Act: -0.0000

Data Index: 132249 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.3371. Min Act: -0.0000

Data Index: 249703 (C4 (Web Text))

Max Activating Token Index: 948