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

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

Neuron 510 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: 0.0619. Min Range: -0.0619

Max Act: 0.0591. Min Act: -0.0003

Data Index: 428532 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0590. Min Act: -0.0002

Data Index: 472140 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0547. Min Act: -0.0002

Data Index: 665481 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0542. Min Act: -0.0002

Data Index: 1192023 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0480. Min Act: -0.0002

Data Index: 827279 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1222366 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0478. Min Act: -0.0002

Data Index: 691903 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0486. Min Act: -0.0002

Data Index: 549766 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0430. Min Act: -0.0002

Data Index: 676219 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1118068 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0455. Min Act: -0.0002

Data Index: 870789 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0445. Min Act: -0.0002

Data Index: 446176 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0372. Min Act: -0.0002

Data Index: 492138 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1198170 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0410. Min Act: -0.0002

Data Index: 523750 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1262015 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0481. Min Act: -0.0002

Data Index: 61894 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0415. Min Act: -0.0002

Data Index: 421552 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0449. Min Act: -0.0002

Data Index: 908172 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0456. Min Act: -0.0002

Data Index: 784370 (C4 (Web Text))

Max Activating Token Index: 66