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

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

Neuron 3374 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: 1.4915. Min Range: -1.4915

Max Act: 1.4549. Min Act: -0.0001

Data Index: 1091619 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 1.4915. Min Range: -1.4915

Max Act: 1.4915. Min Act: -0.0000

Data Index: 1251016 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.9966. Min Act: -0.0000

Data Index: 648238 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.9224. Min Act: -0.0000

Data Index: 207555 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.8902. Min Act: -0.0000

Data Index: 631222 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.8850. Min Act: -0.0000

Data Index: 1228237 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.8493. Min Act: -0.0000

Data Index: 219098 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.8304. Min Act: -0.0000

Data Index: 1339005 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1089945 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.6806. Min Act: -0.0000

Data Index: 1242703 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1164943 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1113099 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.7339. Min Act: -0.0000

Data Index: 978331 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.6832. Min Act: -0.0001

Data Index: 685988 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.7135. Min Act: -0.0000

Data Index: 628521 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.6962. Min Act: -0.0000

Data Index: 465617 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1029549 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.6351. Min Act: -0.0000

Data Index: 61236 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.8598. Min Act: -0.0000

Data Index: 1177550 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.7598. Min Act: -0.0000

Data Index: 1557295 (Python Code)

Max Activating Token Index: 823