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

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

Neuron 487 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.7555. Min Act: -0.0000

Data Index: 75903 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1116214 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.5987. Min Act: -0.0000

Data Index: 769005 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.5901. Min Act: -0.0000

Data Index: 1041474 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.6142. Min Act: -0.0001

Data Index: 681050 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.6280. Min Act: -0.0000

Data Index: 310501 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.6230. Min Act: -0.0000

Data Index: 835742 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.6134. Min Act: -0.0001

Data Index: 316436 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.5872. Min Act: -0.0001

Data Index: 1087777 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.5623. Min Act: -0.0000

Data Index: 937682 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.5642. Min Act: -0.0000

Data Index: 614390 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.5646. Min Act: -0.0000

Data Index: 43387 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.5286. Min Act: -0.0000

Data Index: 400139 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.5529. Min Act: -0.0000

Data Index: 666629 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1131901 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.5437. Min Act: -0.0000

Data Index: 288443 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.5213. Min Act: -0.0000

Data Index: 215166 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.5363. Min Act: -0.0000

Data Index: 1251674 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.5035. Min Act: -0.0001

Data Index: 1263537 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.5145. Min Act: -0.0000

Data Index: 488348 (C4 (Web Text))

Max Activating Token Index: 892