Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3849 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.6804. Min Range: -5.6804

Max Act: 5.6804. Min Act: -0.0001

Data Index: 1441334 (Python Code)

Max Activating Token Index: 966

Text #1

Max Range: 5.6804. Min Range: -5.6804

Max Act: 4.3668. Min Act: -0.0001

Data Index: 1384641 (Python Code)

Max Activating Token Index: 318

Text #2

Max Range: 5.6804. Min Range: -5.6804

Max Act: 4.4137. Min Act: -0.0001

Data Index: 1607726 (Python Code)

Max Activating Token Index: 268

Text #3

Max Range: 5.6804. Min Range: -5.6804

Max Act: 4.1820. Min Act: -0.0001

Data Index: 115393 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 5.6804. Min Range: -5.6804

Max Act: 4.3116. Min Act: -0.0001

Data Index: 1539662 (Python Code)

Max Activating Token Index: 750

Text #5

Max Range: 5.6804. Min Range: -5.6804

Max Act: 4.1148. Min Act: -0.0001

Data Index: 1544536 (Python Code)

Max Activating Token Index: 547

Text #6

Max Range: 5.6804. Min Range: -5.6804

Max Act: 4.0860. Min Act: -0.0001

Data Index: 418410 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 5.6804. Min Range: -5.6804

Max Act: 3.9564. Min Act: -0.0001

Data Index: 1627512 (Python Code)

Max Activating Token Index: 302

Text #8

Max Range: 5.6804. Min Range: -5.6804

Max Act: 3.8940. Min Act: -0.0001

Data Index: 1402144 (Python Code)

Max Activating Token Index: 206

Text #9

Max Range: 5.6804. Min Range: -5.6804

Max Act: 3.3548. Min Act: -0.0001

Data Index: 1512481 (Python Code)

Max Activating Token Index: 518

Text #10

Max Range: 5.6804. Min Range: -5.6804

Max Act: 3.3548. Min Act: -0.0001

Data Index: 128593 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 5.6804. Min Range: -5.6804

Max Act: 3.4985. Min Act: -0.0001

Data Index: 148227 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 5.6804. Min Range: -5.6804

Max Act: 3.2835. Min Act: -0.0001

Data Index: 889672 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 5.6804. Min Range: -5.6804

Max Act: 3.1542. Min Act: -0.0001

Data Index: 1363687 (Python Code)

Max Activating Token Index: 258

Text #14

Max Range: 5.6804. Min Range: -5.6804

Max Act: 3.2895. Min Act: -0.0001

Data Index: 193589 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 5.6804. Min Range: -5.6804

Max Act: 3.2576. Min Act: -0.0001

Data Index: 345427 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 5.6804. Min Range: -5.6804

Max Act: 3.2614. Min Act: -0.0001

Data Index: 1355636 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 5.6804. Min Range: -5.6804

Max Act: 3.2317. Min Act: -0.0000

Data Index: 1115817 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 5.6804. Min Range: -5.6804

Max Act: 3.1803. Min Act: -0.0001

Data Index: 1464346 (Python Code)

Max Activating Token Index: 461

Text #19

Max Range: 5.6804. Min Range: -5.6804

Max Act: 3.1448. Min Act: -0.0000

Data Index: 277511 (C4 (Web Text))

Max Activating Token Index: 486