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

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

Neuron 126 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.9573. Min Act: -0.0000

Data Index: 59187 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7669. Min Act: -0.0000

Data Index: 374547 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.8419. Min Act: -0.0000

Data Index: 878702 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.9534. Min Act: -0.0000

Data Index: 184601 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7985. Min Act: -0.0000

Data Index: 652679 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.8338. Min Act: -0.0000

Data Index: 1152512 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7667. Min Act: -0.0000

Data Index: 434271 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.8259. Min Act: -0.0000

Data Index: 803761 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.8603. Min Act: -0.0000

Data Index: 1329882 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7650. Min Act: -0.0000

Data Index: 296974 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.8486. Min Act: -0.0000

Data Index: 769350 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7682. Min Act: -0.0000

Data Index: 277254 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7709. Min Act: -0.0000

Data Index: 745731 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7484. Min Act: -0.0000

Data Index: 865556 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7671. Min Act: -0.0000

Data Index: 826018 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7907. Min Act: -0.0000

Data Index: 237221 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7931. Min Act: -0.0000

Data Index: 125005 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.8317. Min Act: -0.0000

Data Index: 462816 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7552. Min Act: -0.0000

Data Index: 306367 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7764. Min Act: -0.0000

Data Index: 854638 (C4 (Web Text))

Max Activating Token Index: 214