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

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

Neuron 4192 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0505. Min Act: -0.0002

Data Index: 845785 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0394. Min Act: -0.0002

Data Index: 104025 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1226311 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0373. Min Act: -0.0002

Data Index: 419935 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1207206 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1180896 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0357. Min Act: -0.0002

Data Index: 167973 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0338. Min Act: -0.0002

Data Index: 112742 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1181144 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0319. Min Act: -0.0002

Data Index: 63361 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0304. Min Act: -0.0002

Data Index: 671961 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0302. Min Act: -0.0002

Data Index: 521729 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1358472 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0293. Min Act: -0.0002

Data Index: 262417 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0281. Min Act: -0.0002

Data Index: 1316977 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0297. Min Act: -0.0002

Data Index: 722902 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0295. Min Act: -0.0002

Data Index: 952238 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1035898 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0280. Min Act: -0.0002

Data Index: 134822 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0284. Min Act: -0.0002

Data Index: 181937 (C4 (Web Text))

Max Activating Token Index: 757