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

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

Neuron 3339 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0676. Min Range: -1.0676

Max Act: 1.0676. Min Act: -0.0001

Data Index: 460991 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.9537. Min Act: -0.0001

Data Index: 924545 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.8517. Min Act: -0.0000

Data Index: 1164330 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.8195. Min Act: -0.0001

Data Index: 1056102 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.6957. Min Act: -0.0001

Data Index: 1330552 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.7212. Min Act: -0.0000

Data Index: 310846 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1267396 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.6858. Min Act: -0.0000

Data Index: 960932 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.6184. Min Act: -0.0000

Data Index: 168115 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.6507. Min Act: -0.0001

Data Index: 296864 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.6484. Min Act: -0.0000

Data Index: 822605 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5988. Min Act: -0.0000

Data Index: 678948 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.6198. Min Act: -0.0000

Data Index: 332716 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5872. Min Act: -0.0001

Data Index: 357535 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.6288. Min Act: -0.0000

Data Index: 376611 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.6044. Min Act: -0.0000

Data Index: 462515 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5853. Min Act: -0.0000

Data Index: 713900 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5643. Min Act: -0.0000

Data Index: 637388 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5091. Min Act: -0.0000

Data Index: 218181 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5718. Min Act: -0.0000

Data Index: 575680 (C4 (Web Text))

Max Activating Token Index: 385