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

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

Neuron 5122 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: 3.8749. Min Range: -3.8749

Max Act: 3.8749. Min Act: -0.0000

Data Index: 631110 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.5272. Min Act: -0.0000

Data Index: 233514 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.4242. Min Act: -0.0000

Data Index: 692075 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.2446. Min Act: -0.0000

Data Index: 603909 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.2471. Min Act: -0.0000

Data Index: 1297711 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.5395. Min Act: -0.0000

Data Index: 217231 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.3701. Min Act: -0.0000

Data Index: 496144 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.2703. Min Act: -0.0000

Data Index: 326936 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.2155. Min Act: -0.0000

Data Index: 755379 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.0575. Min Act: -0.0000

Data Index: 1389890 (Python Code)

Max Activating Token Index: 792

Text #10

Max Range: 3.8749. Min Range: -3.8749

Max Act: 2.9255. Min Act: -0.0000

Data Index: 480333 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.0613. Min Act: -0.0000

Data Index: 446742 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 3.8749. Min Range: -3.8749

Max Act: 2.8070. Min Act: -0.0000

Data Index: 748963 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 3.8749. Min Range: -3.8749

Max Act: 2.7502. Min Act: -0.0000

Data Index: 230535 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 3.8749. Min Range: -3.8749

Max Act: 2.6068. Min Act: -0.0000

Data Index: 923796 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 3.8749. Min Range: -3.8749

Max Act: 2.6832. Min Act: -0.0000

Data Index: 803115 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 3.8749. Min Range: -3.8749

Max Act: 2.6664. Min Act: -0.0000

Data Index: 562190 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 3.8749. Min Range: -3.8749

Max Act: 2.6395. Min Act: -0.0000

Data Index: 877015 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 3.8749. Min Range: -3.8749

Max Act: 2.7509. Min Act: -0.0000

Data Index: 998470 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 3.8749. Min Range: -3.8749

Max Act: 2.5945. Min Act: -0.0000

Data Index: 915076 (C4 (Web Text))

Max Activating Token Index: 909