Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2326 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2571. Min Act: -0.0000

Data Index: 669355 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2814. Min Act: -0.0000

Data Index: 137214 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2736. Min Act: -0.0001

Data Index: 922237 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2985. Min Act: -0.0001

Data Index: 1266025 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2807. Min Act: -0.0001

Data Index: 251563 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2595. Min Act: -0.0001

Data Index: 528452 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2363. Min Act: -0.0000

Data Index: 197201 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2623. Min Act: -0.0000

Data Index: 1323705 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2689. Min Act: -0.0001

Data Index: 86478 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2357. Min Act: -0.0001

Data Index: 1283580 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1200946 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.1925. Min Act: -0.0000

Data Index: 835563 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2338. Min Act: -0.0000

Data Index: 809293 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2403. Min Act: -0.0000

Data Index: 961193 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2329. Min Act: -0.0000

Data Index: 734089 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2177. Min Act: -0.0001

Data Index: 535598 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2332. Min Act: -0.0000

Data Index: 186335 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2295. Min Act: -0.0000

Data Index: 823859 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2122. Min Act: -0.0000

Data Index: 140349 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2165. Min Act: -0.0000

Data Index: 557618 (C4 (Web Text))

Max Activating Token Index: 644