Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4994 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.7294. Min Act: -0.0000

Data Index: 754978 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4362. Min Act: -0.0000

Data Index: 427516 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1265783 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5062. Min Act: -0.0000

Data Index: 1182642 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5135. Min Act: -0.0000

Data Index: 955983 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4906. Min Act: -0.0000

Data Index: 730609 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4333. Min Act: -0.0000

Data Index: 887423 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4651. Min Act: -0.0000

Data Index: 534487 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4341. Min Act: -0.0000

Data Index: 757857 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4233. Min Act: -0.0000

Data Index: 459538 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4538. Min Act: -0.0000

Data Index: 974296 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4300. Min Act: -0.0000

Data Index: 291909 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4147. Min Act: -0.0000

Data Index: 919867 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4299. Min Act: -0.0000

Data Index: 1359492 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1213264 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4311. Min Act: -0.0000

Data Index: 1293863 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4125. Min Act: -0.0000

Data Index: 230419 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4119. Min Act: -0.0000

Data Index: 1020827 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4193. Min Act: -0.0000

Data Index: 86315 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.3861. Min Act: -0.0000

Data Index: 1239716 (C4 (Web Text))

Max Activating Token Index: 361