Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5015 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8988. Min Act: -0.0002

Data Index: 247423 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8572. Min Act: -0.0002

Data Index: 443876 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8570. Min Act: -0.0002

Data Index: 950736 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8433. Min Act: -0.0002

Data Index: 769090 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8410. Min Act: -0.0002

Data Index: 1335707 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8361. Min Act: -0.0002

Data Index: 39000 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8480. Min Act: -0.0002

Data Index: 441917 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8413. Min Act: -0.0002

Data Index: 1268977 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8240. Min Act: -0.0002

Data Index: 993769 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8235. Min Act: -0.0002

Data Index: 666706 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8149. Min Act: -0.0002

Data Index: 1246686 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8184. Min Act: -0.0002

Data Index: 579616 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8297. Min Act: -0.0002

Data Index: 1156660 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8234. Min Act: -0.0002

Data Index: 1149395 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8223. Min Act: -0.0002

Data Index: 274367 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8100. Min Act: -0.0002

Data Index: 575588 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8041. Min Act: -0.0002

Data Index: 348171 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8183. Min Act: -0.0002

Data Index: 100261 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8098. Min Act: -0.0002

Data Index: 507942 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8006. Min Act: -0.0002

Data Index: 471478 (C4 (Web Text))

Max Activating Token Index: 80