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

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

Neuron 4984 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4232. Min Range: -3.4232

Max Act: 3.4232. Min Act: -0.0000

Data Index: 245358 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.5168. Min Act: -0.0000

Data Index: 1188870 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.6586. Min Act: -0.0000

Data Index: 921576 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.2990. Min Act: -0.0000

Data Index: 72968 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 3.4232. Min Range: -3.4232

Max Act: 1.7218. Min Act: -0.0000

Data Index: 1239314 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.1917. Min Act: -0.0000

Data Index: 931978 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.1822. Min Act: -0.0000

Data Index: 660532 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.1538. Min Act: -0.0000

Data Index: 124671 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.0113. Min Act: -0.0000

Data Index: 558461 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.1187. Min Act: -0.0000

Data Index: 501806 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.2157. Min Act: -0.0000

Data Index: 401341 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.3072. Min Act: -0.0000

Data Index: 85579 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.0739. Min Act: -0.0000

Data Index: 673890 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.0840. Min Act: -0.0000

Data Index: 914348 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 3.4232. Min Range: -3.4232

Max Act: 1.9808. Min Act: -0.0000

Data Index: 1055824 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.2569. Min Act: -0.0000

Data Index: 239282 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 3.4232. Min Range: -3.4232

Max Act: 1.9786. Min Act: -0.0000

Data Index: 744046 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 3.4232. Min Range: -3.4232

Max Act: 1.9530. Min Act: -0.0000

Data Index: 400146 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 3.4232. Min Range: -3.4232

Max Act: 1.9834. Min Act: -0.0000

Data Index: 5149 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.0016. Min Act: -0.0000

Data Index: 27796 (C4 (Web Text))

Max Activating Token Index: 816