Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 291 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1629. Min Act: -0.0002

Data Index: 468036 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1567. Min Act: -0.0001

Data Index: 1195570 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1572076 (Python Code)

Max Activating Token Index: 539

Text #3

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1475. Min Act: -0.0000

Data Index: 1479755 (Python Code)

Max Activating Token Index: 490

Text #4

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1470. Min Act: -0.0001

Data Index: 1616290 (Python Code)

Max Activating Token Index: 494

Text #5

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1417. Min Act: -0.0000

Data Index: 1389300 (Python Code)

Max Activating Token Index: 614

Text #6

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1577520 (Python Code)

Max Activating Token Index: 783

Text #7

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1434. Min Act: -0.0001

Data Index: 1654861 (Python Code)

Max Activating Token Index: 18

Text #8

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1292. Min Act: -0.0002

Data Index: 1177497 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1385. Min Act: -0.0000

Data Index: 1557245 (Python Code)

Max Activating Token Index: 36

Text #10

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1444. Min Act: -0.0001

Data Index: 1472299 (Python Code)

Max Activating Token Index: 978

Text #11

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1269. Min Act: -0.0001

Data Index: 1451785 (Python Code)

Max Activating Token Index: 421

Text #12

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1428. Min Act: -0.0001

Data Index: 1365725 (Python Code)

Max Activating Token Index: 131

Text #13

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1309. Min Act: -0.0002

Data Index: 1490183 (Python Code)

Max Activating Token Index: 239

Text #14

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1305. Min Act: -0.0002

Data Index: 1000640 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1264. Min Act: -0.0002

Data Index: 572556 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1209. Min Act: -0.0002

Data Index: 1132620 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1312. Min Act: -0.0001

Data Index: 1577541 (Python Code)

Max Activating Token Index: 29

Text #18

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1206. Min Act: -0.0002

Data Index: 383668 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1261. Min Act: -0.0002

Data Index: 40451 (C4 (Web Text))

Max Activating Token Index: 984