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

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

Neuron 1917 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0246. Min Range: -3.0246

Max Act: 3.0100. Min Act: -0.0000

Data Index: 810801 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 3.0246. Min Range: -3.0246

Max Act: 3.0246. Min Act: -0.0000

Data Index: 1322413 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 3.0246. Min Range: -3.0246

Max Act: 2.9575. Min Act: -0.0000

Data Index: 1242916 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 3.0246. Min Range: -3.0246

Max Act: 2.5911. Min Act: -0.0000

Data Index: 161468 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 3.0246. Min Range: -3.0246

Max Act: 2.8286. Min Act: -0.0000

Data Index: 793381 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 3.0246. Min Range: -3.0246

Max Act: 2.7669. Min Act: -0.0000

Data Index: 1090869 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 3.0246. Min Range: -3.0246

Max Act: 2.5329. Min Act: -0.0000

Data Index: 841401 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 3.0246. Min Range: -3.0246

Max Act: 2.5237. Min Act: -0.0000

Data Index: 148414 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 3.0246. Min Range: -3.0246

Max Act: 2.3623. Min Act: -0.0000

Data Index: 465684 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 3.0246. Min Range: -3.0246

Max Act: 2.7124. Min Act: -0.0000

Data Index: 67578 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 3.0246. Min Range: -3.0246

Max Act: 2.4529. Min Act: -0.0000

Data Index: 498093 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 3.0246. Min Range: -3.0246

Max Act: 2.3876. Min Act: -0.0000

Data Index: 759784 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.0246. Min Range: -3.0246

Max Act: 2.3374. Min Act: -0.0000

Data Index: 191635 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 3.0246. Min Range: -3.0246

Max Act: 2.2295. Min Act: -0.0000

Data Index: 279241 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 3.0246. Min Range: -3.0246

Max Act: 2.1141. Min Act: -0.0000

Data Index: 142230 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 3.0246. Min Range: -3.0246

Max Act: 1.9953. Min Act: -0.0000

Data Index: 789311 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 3.0246. Min Range: -3.0246

Max Act: 2.3186. Min Act: -0.0000

Data Index: 398296 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 3.0246. Min Range: -3.0246

Max Act: 2.2959. Min Act: -0.0000

Data Index: 1343338 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 3.0246. Min Range: -3.0246

Max Act: 1.8316. Min Act: -0.0000

Data Index: 61976 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 3.0246. Min Range: -3.0246

Max Act: 2.0232. Min Act: -0.0000

Data Index: 999750 (C4 (Web Text))

Max Activating Token Index: 206