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

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

Neuron 4770 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.6077. Min Act: -0.0000

Data Index: 361057 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.5374. Min Act: -0.0000

Data Index: 958008 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.5530. Min Act: -0.0000

Data Index: 270898 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.5526. Min Act: -0.0000

Data Index: 497397 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.4862. Min Act: -0.0000

Data Index: 713933 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.4902. Min Act: -0.0000

Data Index: 204889 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.4655. Min Act: -0.0000

Data Index: 1367286 (Python Code)

Max Activating Token Index: 576

Text #7

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.4622. Min Act: -0.0000

Data Index: 644974 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.4424. Min Act: -0.0000

Data Index: 808087 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.3901. Min Act: -0.0000

Data Index: 629174 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.3739. Min Act: -0.0000

Data Index: 788522 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.3905. Min Act: -0.0000

Data Index: 331051 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1515959 (Python Code)

Max Activating Token Index: 346

Text #13

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.3527. Min Act: -0.0000

Data Index: 1436017 (Python Code)

Max Activating Token Index: 205

Text #14

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1631587 (Python Code)

Max Activating Token Index: 472

Text #15

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.3309. Min Act: -0.0000

Data Index: 51284 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.3661. Min Act: -0.0000

Data Index: 656245 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.3411. Min Act: -0.0000

Data Index: 1634350 (Python Code)

Max Activating Token Index: 1014

Text #18

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1496874 (Python Code)

Max Activating Token Index: 622

Text #19

Max Range: 0.6077. Min Range: -0.6077

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1289397 (C4 (Web Text))

Max Activating Token Index: 319