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

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

Neuron 2159 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: 0.1549. Min Range: -0.1549

Max Act: 0.1549. Min Act: -0.0003

Data Index: 183873 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1481. Min Act: -0.0003

Data Index: 917799 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1492. Min Act: -0.0003

Data Index: 527502 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1485. Min Act: -0.0003

Data Index: 1091563 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1504. Min Act: -0.0003

Data Index: 398808 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1439. Min Act: -0.0003

Data Index: 481516 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1438. Min Act: -0.0003

Data Index: 79322 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1382. Min Act: -0.0003

Data Index: 560326 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1374. Min Act: -0.0003

Data Index: 1361043 (Python Code)

Max Activating Token Index: 449

Text #9

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1331. Min Act: -0.0003

Data Index: 1604265 (Python Code)

Max Activating Token Index: 304

Text #10

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1422. Min Act: -0.0003

Data Index: 337077 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1290. Min Act: -0.0003

Data Index: 1531323 (Python Code)

Max Activating Token Index: 899

Text #12

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1274. Min Act: -0.0003

Data Index: 566260 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1255. Min Act: -0.0003

Data Index: 1135641 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1212. Min Act: -0.0003

Data Index: 1371344 (Python Code)

Max Activating Token Index: 573

Text #15

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1284. Min Act: -0.0003

Data Index: 1409502 (Python Code)

Max Activating Token Index: 141

Text #16

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1331. Min Act: -0.0003

Data Index: 1607441 (Python Code)

Max Activating Token Index: 189

Text #17

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1095. Min Act: -0.0003

Data Index: 1528911 (Python Code)

Max Activating Token Index: 833

Text #18

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1331. Min Act: -0.0003

Data Index: 826909 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1273. Min Act: -0.0003

Data Index: 1617178 (Python Code)

Max Activating Token Index: 67