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

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

Neuron 1482 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: 2.0026. Min Range: -2.0026

Max Act: 2.0026. Min Act: 0.0000

Data Index: 869291 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 2.0026. Min Range: -2.0026

Max Act: 1.4921. Min Act: -0.0000

Data Index: 1175179 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 2.0026. Min Range: -2.0026

Max Act: 1.4809. Min Act: -0.0000

Data Index: 327778 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 2.0026. Min Range: -2.0026

Max Act: 1.4572. Min Act: -0.0000

Data Index: 492107 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 2.0026. Min Range: -2.0026

Max Act: 1.4358. Min Act: 0.0000

Data Index: 1281386 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 2.0026. Min Range: -2.0026

Max Act: 1.3852. Min Act: -0.0000

Data Index: 1218870 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 2.0026. Min Range: -2.0026

Max Act: 1.3691. Min Act: -0.0000

Data Index: 281331 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 2.0026. Min Range: -2.0026

Max Act: 1.3324. Min Act: -0.0000

Data Index: 1268456 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 2.0026. Min Range: -2.0026

Max Act: 1.3403. Min Act: -0.0000

Data Index: 134331 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 2.0026. Min Range: -2.0026

Max Act: 1.2578. Min Act: -0.0000

Data Index: 542487 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 2.0026. Min Range: -2.0026

Max Act: 1.3964. Min Act: -0.0000

Data Index: 1198303 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 2.0026. Min Range: -2.0026

Max Act: 1.3124. Min Act: -0.0000

Data Index: 304609 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 2.0026. Min Range: -2.0026

Max Act: 1.3146. Min Act: -0.0000

Data Index: 985884 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 2.0026. Min Range: -2.0026

Max Act: 1.2813. Min Act: -0.0000

Data Index: 175934 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 2.0026. Min Range: -2.0026

Max Act: 1.2168. Min Act: -0.0000

Data Index: 38195 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 2.0026. Min Range: -2.0026

Max Act: 1.1847. Min Act: -0.0000

Data Index: 1258150 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 2.0026. Min Range: -2.0026

Max Act: 1.2540. Min Act: -0.0000

Data Index: 503961 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 2.0026. Min Range: -2.0026

Max Act: 1.2290. Min Act: -0.0000

Data Index: 281541 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 2.0026. Min Range: -2.0026

Max Act: 1.2348. Min Act: -0.0000

Data Index: 22410 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 2.0026. Min Range: -2.0026

Max Act: 1.1747. Min Act: -0.0000

Data Index: 789843 (C4 (Web Text))

Max Activating Token Index: 452