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

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

Neuron 4263 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7821. Min Act: -0.0000

Data Index: 56284 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1267683 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7561. Min Act: -0.0000

Data Index: 278967 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7398. Min Act: -0.0000

Data Index: 1169435 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1243503 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6159. Min Act: -0.0000

Data Index: 740764 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6126. Min Act: -0.0000

Data Index: 997080 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6086. Min Act: -0.0000

Data Index: 805122 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6015. Min Act: -0.0000

Data Index: 410796 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.5716. Min Act: -0.0000

Data Index: 552350 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.5475. Min Act: -0.0000

Data Index: 344401 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.5302. Min Act: -0.0000

Data Index: 890376 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.5318. Min Act: -0.0000

Data Index: 915060 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.5052. Min Act: -0.0000

Data Index: 199879 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1060461 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.4986. Min Act: -0.0000

Data Index: 574371 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.4912. Min Act: -0.0000

Data Index: 819755 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.5271. Min Act: -0.0000

Data Index: 1254103 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1159048 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.4942. Min Act: -0.0000

Data Index: 250674 (C4 (Web Text))

Max Activating Token Index: 861