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

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

Neuron 3173 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: 0.0618. Min Range: -0.0618

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1627184 (Python Code)

Max Activating Token Index: 72

Text #1

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0433. Min Act: -0.0002

Data Index: 514573 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0338. Min Act: -0.0002

Data Index: 728402 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0398. Min Act: -0.0002

Data Index: 865904 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0340. Min Act: -0.0002

Data Index: 934439 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0352. Min Act: -0.0002

Data Index: 975390 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0341. Min Act: -0.0002

Data Index: 204459 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0353. Min Act: -0.0002

Data Index: 76364 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0349. Min Act: -0.0002

Data Index: 503719 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0319. Min Act: -0.0002

Data Index: 422100 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0311. Min Act: -0.0002

Data Index: 338655 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0334. Min Act: -0.0002

Data Index: 342012 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1151044 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0322. Min Act: -0.0002

Data Index: 693511 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0336. Min Act: -0.0002

Data Index: 89338 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0294. Min Act: -0.0002

Data Index: 309823 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0317. Min Act: -0.0002

Data Index: 448938 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1079458 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0311. Min Act: -0.0002

Data Index: 840363 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1248976 (C4 (Web Text))

Max Activating Token Index: 470