Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1432 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1566. Min Act: -0.0003

Data Index: 1175962 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1590. Min Act: -0.0003

Data Index: 196402 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1533. Min Act: -0.0003

Data Index: 323117 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1473. Min Act: -0.0003

Data Index: 1184628 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1459. Min Act: -0.0002

Data Index: 467479 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1407. Min Act: -0.0003

Data Index: 427195 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1396. Min Act: -0.0003

Data Index: 1242988 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1445. Min Act: -0.0003

Data Index: 1193835 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1445. Min Act: -0.0003

Data Index: 19346 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1464. Min Act: -0.0002

Data Index: 1586174 (Python Code)

Max Activating Token Index: 850

Text #10

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1442. Min Act: -0.0003

Data Index: 1025979 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1349. Min Act: -0.0003

Data Index: 580351 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1273. Min Act: -0.0003

Data Index: 1291148 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1361. Min Act: -0.0003

Data Index: 750305 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1259. Min Act: -0.0003

Data Index: 789531 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1264. Min Act: -0.0003

Data Index: 1136936 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1277. Min Act: -0.0003

Data Index: 840963 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1297. Min Act: -0.0003

Data Index: 1575834 (Python Code)

Max Activating Token Index: 529

Text #18

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1144. Min Act: -0.0003

Data Index: 783596 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1170. Min Act: -0.0003

Data Index: 1491454 (Python Code)

Max Activating Token Index: 372