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

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

Neuron 3345 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6158. Min Range: -3.6158

Max Act: 3.6158. Min Act: -0.0000

Data Index: 1272934 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 3.6158. Min Range: -3.6158

Max Act: 3.2650. Min Act: -0.0001

Data Index: 1037568 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 3.6158. Min Range: -3.6158

Max Act: 2.9099. Min Act: -0.0000

Data Index: 696568 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 3.6158. Min Range: -3.6158

Max Act: 2.6597. Min Act: -0.0001

Data Index: 1076020 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 3.6158. Min Range: -3.6158

Max Act: 2.4854. Min Act: -0.0000

Data Index: 652638 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 3.6158. Min Range: -3.6158

Max Act: 2.5359. Min Act: -0.0000

Data Index: 901032 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 3.6158. Min Range: -3.6158

Max Act: 2.7107. Min Act: -0.0001

Data Index: 606830 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 3.6158. Min Range: -3.6158

Max Act: 2.4490. Min Act: -0.0001

Data Index: 445719 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 3.6158. Min Range: -3.6158

Max Act: 2.5306. Min Act: -0.0000

Data Index: 989785 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 3.6158. Min Range: -3.6158

Max Act: 2.7538. Min Act: -0.0000

Data Index: 404790 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 3.6158. Min Range: -3.6158

Max Act: 2.6417. Min Act: -0.0000

Data Index: 766775 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 3.6158. Min Range: -3.6158

Max Act: 2.3329. Min Act: -0.0000

Data Index: 852392 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 3.6158. Min Range: -3.6158

Max Act: 2.4391. Min Act: -0.0000

Data Index: 752370 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 3.6158. Min Range: -3.6158

Max Act: 2.1515. Min Act: -0.0000

Data Index: 1125026 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 3.6158. Min Range: -3.6158

Max Act: 2.1213. Min Act: -0.0000

Data Index: 728829 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 3.6158. Min Range: -3.6158

Max Act: 2.0922. Min Act: -0.0000

Data Index: 1266752 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 3.6158. Min Range: -3.6158

Max Act: 2.1646. Min Act: -0.0000

Data Index: 745159 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 3.6158. Min Range: -3.6158

Max Act: 2.1664. Min Act: -0.0000

Data Index: 1351384 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 3.6158. Min Range: -3.6158

Max Act: 2.1556. Min Act: -0.0001

Data Index: 454131 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 3.6158. Min Range: -3.6158

Max Act: 2.0329. Min Act: -0.0000

Data Index: 339469 (C4 (Web Text))

Max Activating Token Index: 973