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

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

Neuron 975 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.6212. Min Act: -0.0000

Data Index: 767448 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.6411. Min Act: -0.0000

Data Index: 798999 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.6120. Min Act: -0.0000

Data Index: 170419 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5831. Min Act: -0.0000

Data Index: 263968 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5781. Min Act: -0.0000

Data Index: 182838 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1032551 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1240299 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5114. Min Act: -0.0000

Data Index: 757293 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5169. Min Act: -0.0000

Data Index: 357471 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4963. Min Act: -0.0000

Data Index: 307294 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4945. Min Act: -0.0000

Data Index: 672081 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4905. Min Act: -0.0000

Data Index: 753835 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4692. Min Act: -0.0000

Data Index: 942143 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4622. Min Act: -0.0000

Data Index: 66932 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4635. Min Act: -0.0000

Data Index: 202317 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4632. Min Act: -0.0000

Data Index: 1288904 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4582. Min Act: -0.0000

Data Index: 1117624 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4384. Min Act: -0.0000

Data Index: 580436 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4572. Min Act: -0.0000

Data Index: 28723 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4260. Min Act: -0.0000

Data Index: 918956 (C4 (Web Text))

Max Activating Token Index: 694