Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2957 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2381. Min Act: -0.0003

Data Index: 350850 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2315. Min Act: -0.0003

Data Index: 292472 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2364. Min Act: -0.0003

Data Index: 1278697 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2048. Min Act: -0.0003

Data Index: 1306740 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2071. Min Act: -0.0003

Data Index: 98696 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1707. Min Act: -0.0003

Data Index: 913911 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1800. Min Act: -0.0003

Data Index: 1192828 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1828. Min Act: -0.0003

Data Index: 776195 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1455. Min Act: -0.0003

Data Index: 960513 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1482. Min Act: -0.0003

Data Index: 410237 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1697. Min Act: -0.0003

Data Index: 1106038 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1645. Min Act: -0.0003

Data Index: 289380 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1591. Min Act: -0.0003

Data Index: 792573 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1595. Min Act: -0.0003

Data Index: 1357518 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1631. Min Act: -0.0003

Data Index: 523978 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1518. Min Act: -0.0003

Data Index: 1214594 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1681. Min Act: -0.0003

Data Index: 64469 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1590. Min Act: -0.0003

Data Index: 972935 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1722. Min Act: -0.0003

Data Index: 1277571 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1666. Min Act: -0.0003

Data Index: 148595 (C4 (Web Text))

Max Activating Token Index: 45