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

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

Neuron 3482 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: 0.1118. Min Range: -0.1118

Max Act: 0.1118. Min Act: -0.0002

Data Index: 1290517 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1329823 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0788. Min Act: -0.0002

Data Index: 430228 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0701. Min Act: -0.0002

Data Index: 316300 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0724. Min Act: -0.0002

Data Index: 1326146 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0773. Min Act: -0.0002

Data Index: 329282 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1113579 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1113505 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1167533 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1325841 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1085124 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0606. Min Act: -0.0002

Data Index: 226758 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0705. Min Act: -0.0002

Data Index: 718139 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0682. Min Act: -0.0002

Data Index: 715467 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0649. Min Act: -0.0002

Data Index: 465035 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1001311 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0638. Min Act: -0.0002

Data Index: 618020 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0638. Min Act: -0.0002

Data Index: 140256 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0613. Min Act: -0.0002

Data Index: 863519 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0662. Min Act: -0.0002

Data Index: 203416 (C4 (Web Text))

Max Activating Token Index: 671