Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 697 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1973. Min Act: -0.0000

Data Index: 732550 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1966. Min Act: -0.0000

Data Index: 739349 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1707. Min Act: -0.0000

Data Index: 74300 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1769. Min Act: -0.0000

Data Index: 892622 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1633. Min Act: -0.0000

Data Index: 424047 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1642. Min Act: -0.0000

Data Index: 1089943 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1448. Min Act: -0.0000

Data Index: 1075749 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1081224 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1350568 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1530. Min Act: -0.0000

Data Index: 828214 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1455. Min Act: -0.0000

Data Index: 838906 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1442. Min Act: -0.0000

Data Index: 438959 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1011334 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1379. Min Act: -0.0000

Data Index: 1278998 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1418. Min Act: -0.0000

Data Index: 704176 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1400. Min Act: -0.0000

Data Index: 482269 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1374. Min Act: -0.0000

Data Index: 59792 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1413. Min Act: -0.0000

Data Index: 272568 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1351. Min Act: -0.0000

Data Index: 217190 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1315. Min Act: -0.0000

Data Index: 113002 (C4 (Web Text))

Max Activating Token Index: 352