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

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

Neuron 2010 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1440. Min Range: -1.1440

Max Act: 1.1440. Min Act: -0.0000

Data Index: 871380 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 1.1440. Min Range: -1.1440

Max Act: 1.0200. Min Act: -0.0000

Data Index: 948533 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.9410. Min Act: -0.0000

Data Index: 922042 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.9158. Min Act: -0.0000

Data Index: 1256635 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.9591. Min Act: -0.0000

Data Index: 254650 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8768. Min Act: -0.0000

Data Index: 548170 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8589. Min Act: -0.0000

Data Index: 45412 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8987. Min Act: -0.0000

Data Index: 896687 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1157820 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.9320. Min Act: -0.0001

Data Index: 1341229 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1135153 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8728. Min Act: -0.0000

Data Index: 627930 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.9190. Min Act: -0.0000

Data Index: 299154 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8669. Min Act: -0.0000

Data Index: 1026720 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8481. Min Act: -0.0000

Data Index: 1030870 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.9266. Min Act: -0.0000

Data Index: 1027430 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8091. Min Act: -0.0000

Data Index: 913211 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8269. Min Act: -0.0000

Data Index: 934126 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8298. Min Act: -0.0000

Data Index: 457235 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8700. Min Act: -0.0000

Data Index: 692411 (C4 (Web Text))

Max Activating Token Index: 881