Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1531 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0470. Min Act: -0.0004

Data Index: 908330 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0449. Min Act: -0.0004

Data Index: 1336460 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0458. Min Act: -0.0004

Data Index: 443672 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0444. Min Act: -0.0004

Data Index: 216017 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0443. Min Act: -0.0004

Data Index: 732725 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0442. Min Act: -0.0004

Data Index: 802910 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0443. Min Act: -0.0004

Data Index: 230166 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0442. Min Act: -0.0004

Data Index: 978751 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0434. Min Act: -0.0004

Data Index: 610053 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0439. Min Act: -0.0004

Data Index: 720346 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0438. Min Act: -0.0004

Data Index: 445229 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0437. Min Act: -0.0004

Data Index: 112904 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0427. Min Act: -0.0004

Data Index: 513445 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0426. Min Act: -0.0004

Data Index: 504163 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0435. Min Act: -0.0004

Data Index: 1334477 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0425. Min Act: -0.0004

Data Index: 1189739 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0432. Min Act: -0.0004

Data Index: 137490 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0429. Min Act: -0.0004

Data Index: 2503 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0428. Min Act: -0.0004

Data Index: 918820 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0427. Min Act: -0.0004

Data Index: 207747 (C4 (Web Text))

Max Activating Token Index: 662