Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 403 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1961. Min Act: -0.0001

Data Index: 1638750 (Python Code)

Max Activating Token Index: 77

Text #1

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1858. Min Act: -0.0001

Data Index: 1464921 (Python Code)

Max Activating Token Index: 284

Text #2

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1617. Min Act: -0.0001

Data Index: 1632279 (Python Code)

Max Activating Token Index: 378

Text #3

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1508. Min Act: -0.0000

Data Index: 1539742 (Python Code)

Max Activating Token Index: 638

Text #4

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1512. Min Act: -0.0001

Data Index: 1627515 (Python Code)

Max Activating Token Index: 963

Text #5

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1580. Min Act: -0.0001

Data Index: 1571930 (Python Code)

Max Activating Token Index: 506

Text #6

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1645486 (Python Code)

Max Activating Token Index: 197

Text #7

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1375. Min Act: -0.0001

Data Index: 1588406 (Python Code)

Max Activating Token Index: 380

Text #8

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1467. Min Act: -0.0000

Data Index: 1391469 (Python Code)

Max Activating Token Index: 541

Text #9

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1414. Min Act: -0.0000

Data Index: 1575853 (Python Code)

Max Activating Token Index: 339

Text #10

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1434. Min Act: -0.0001

Data Index: 130153 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1414. Min Act: -0.0000

Data Index: 1536919 (Python Code)

Max Activating Token Index: 112

Text #12

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1463. Min Act: -0.0001

Data Index: 1518954 (Python Code)

Max Activating Token Index: 400

Text #13

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1412. Min Act: -0.0001

Data Index: 1523230 (Python Code)

Max Activating Token Index: 281

Text #14

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1408. Min Act: -0.0000

Data Index: 1507357 (Python Code)

Max Activating Token Index: 40

Text #15

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1300. Min Act: -0.0000

Data Index: 1471911 (Python Code)

Max Activating Token Index: 457

Text #16

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1394. Min Act: -0.0001

Data Index: 1370886 (Python Code)

Max Activating Token Index: 907

Text #17

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1328. Min Act: -0.0001

Data Index: 510469 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1325. Min Act: -0.0000

Data Index: 1372375 (Python Code)

Max Activating Token Index: 1009

Text #19

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1355. Min Act: -0.0001

Data Index: 1385816 (Python Code)

Max Activating Token Index: 173