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

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

Neuron 1321 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: 1.9710. Min Range: -1.9710

Max Act: 1.9710. Min Act: -0.0000

Data Index: 850581 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 1.9710. Min Range: -1.9710

Max Act: 1.7686. Min Act: -0.0000

Data Index: 296643 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 1.9710. Min Range: -1.9710

Max Act: 1.8570. Min Act: -0.0000

Data Index: 1023974 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 1.9710. Min Range: -1.9710

Max Act: 1.6795. Min Act: -0.0000

Data Index: 239534 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 1.9710. Min Range: -1.9710

Max Act: 1.6324. Min Act: -0.0000

Data Index: 679110 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 1.9710. Min Range: -1.9710

Max Act: 1.6402. Min Act: -0.0000

Data Index: 915258 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 1.9710. Min Range: -1.9710

Max Act: 1.5416. Min Act: -0.0000

Data Index: 665336 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 1.9710. Min Range: -1.9710

Max Act: 1.4480. Min Act: 0.0000

Data Index: 529735 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 1.9710. Min Range: -1.9710

Max Act: 1.5321. Min Act: -0.0000

Data Index: 176249 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 1.9710. Min Range: -1.9710

Max Act: 1.6099. Min Act: -0.0000

Data Index: 117879 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 1.9710. Min Range: -1.9710

Max Act: 1.5205. Min Act: -0.0000

Data Index: 166109 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 1.9710. Min Range: -1.9710

Max Act: 1.4940. Min Act: 0.0001

Data Index: 552424 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 1.9710. Min Range: -1.9710

Max Act: 1.4725. Min Act: -0.0000

Data Index: 703248 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 1.9710. Min Range: -1.9710

Max Act: 1.3223. Min Act: -0.0000

Data Index: 828242 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 1.9710. Min Range: -1.9710

Max Act: 1.4054. Min Act: -0.0000

Data Index: 1303791 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 1.9710. Min Range: -1.9710

Max Act: 1.3717. Min Act: -0.0000

Data Index: 17000 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 1.9710. Min Range: -1.9710

Max Act: 1.2712. Min Act: -0.0000

Data Index: 403914 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 1.9710. Min Range: -1.9710

Max Act: 1.2357. Min Act: 0.0001

Data Index: 386650 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 1.9710. Min Range: -1.9710

Max Act: 1.2682. Min Act: 0.0001

Data Index: 1241116 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 1.9710. Min Range: -1.9710

Max Act: 1.2583. Min Act: -0.0000

Data Index: 445503 (C4 (Web Text))

Max Activating Token Index: 451