Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 966 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7039. Min Act: -0.0002

Data Index: 183140 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6932. Min Act: -0.0002

Data Index: 402225 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.8020. Min Act: -0.0002

Data Index: 324494 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7335. Min Act: -0.0002

Data Index: 336297 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7292. Min Act: -0.0002

Data Index: 1275498 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6868. Min Act: -0.0002

Data Index: 1281890 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6091. Min Act: -0.0002

Data Index: 777360 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6002. Min Act: -0.0002

Data Index: 899806 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6195. Min Act: -0.0002

Data Index: 738745 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6689. Min Act: -0.0002

Data Index: 656857 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6694. Min Act: -0.0002

Data Index: 1267139 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.5484. Min Act: -0.0002

Data Index: 612270 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6146. Min Act: -0.0002

Data Index: 1229451 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6493. Min Act: -0.0002

Data Index: 1231567 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6191. Min Act: -0.0002

Data Index: 1318908 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.5911. Min Act: -0.0002

Data Index: 683368 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6327. Min Act: -0.0002

Data Index: 1189809 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.5890. Min Act: -0.0002

Data Index: 584173 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6435. Min Act: -0.0002

Data Index: 78496 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6481. Min Act: -0.0002

Data Index: 4970 (C4 (Web Text))

Max Activating Token Index: 730