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

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

Neuron 2382 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: 0.1764. Min Range: -0.1764

Max Act: 0.1764. Min Act: -0.0003

Data Index: 1273469 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1646. Min Act: -0.0003

Data Index: 1248322 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1687. Min Act: -0.0003

Data Index: 3982 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1677. Min Act: -0.0003

Data Index: 144715 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1672. Min Act: -0.0003

Data Index: 950701 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1488. Min Act: -0.0003

Data Index: 22922 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1596. Min Act: -0.0003

Data Index: 516241 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1478. Min Act: -0.0003

Data Index: 346574 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1520. Min Act: -0.0003

Data Index: 118981 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1463. Min Act: -0.0003

Data Index: 89586 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1455. Min Act: -0.0003

Data Index: 310654 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1574. Min Act: -0.0003

Data Index: 240662 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1338. Min Act: -0.0003

Data Index: 1342039 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1377. Min Act: -0.0003

Data Index: 317605 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1280. Min Act: -0.0003

Data Index: 264645 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1328. Min Act: -0.0003

Data Index: 115669 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1265. Min Act: -0.0003

Data Index: 332785 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1301. Min Act: -0.0003

Data Index: 752594 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1361. Min Act: -0.0003

Data Index: 648052 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1373. Min Act: -0.0003

Data Index: 38330 (C4 (Web Text))

Max Activating Token Index: 577