Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3884 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3597. Min Act: -0.0000

Data Index: 282668 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2910. Min Act: -0.0001

Data Index: 165863 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2643. Min Act: -0.0000

Data Index: 247318 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2679. Min Act: -0.0000

Data Index: 616091 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2667. Min Act: -0.0000

Data Index: 432119 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1183829 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2660. Min Act: -0.0000

Data Index: 1282906 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2569. Min Act: -0.0000

Data Index: 811070 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2543. Min Act: -0.0000

Data Index: 21713 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2459. Min Act: -0.0000

Data Index: 917177 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2430. Min Act: -0.0000

Data Index: 70503 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2471. Min Act: -0.0000

Data Index: 317398 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2388. Min Act: -0.0000

Data Index: 330023 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2238. Min Act: -0.0000

Data Index: 543005 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1175488 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2233. Min Act: -0.0000

Data Index: 155209 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2145. Min Act: -0.0000

Data Index: 513601 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2110. Min Act: -0.0001

Data Index: 982837 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2166. Min Act: -0.0001

Data Index: 639786 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2151. Min Act: -0.0000

Data Index: 1340467 (C4 (Web Text))

Max Activating Token Index: 977