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

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

Neuron 2403 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.3281. Min Act: -0.0000

Data Index: 1502551 (Python Code)

Max Activating Token Index: 124

Text #1

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.2170. Min Act: -0.0000

Data Index: 749100 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.1904. Min Act: -0.0001

Data Index: 1451383 (Python Code)

Max Activating Token Index: 606

Text #3

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1376701 (Python Code)

Max Activating Token Index: 1007

Text #4

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.1875. Min Act: -0.0000

Data Index: 1446363 (Python Code)

Max Activating Token Index: 613

Text #5

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.1815. Min Act: -0.0000

Data Index: 459581 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.1494. Min Act: -0.0000

Data Index: 1580270 (Python Code)

Max Activating Token Index: 80

Text #7

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.1468. Min Act: -0.0000

Data Index: 1558353 (Python Code)

Max Activating Token Index: 609

Text #8

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.1457. Min Act: -0.0000

Data Index: 1630060 (Python Code)

Max Activating Token Index: 36

Text #9

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.1453. Min Act: -0.0000

Data Index: 1369510 (Python Code)

Max Activating Token Index: 678

Text #10

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1373705 (Python Code)

Max Activating Token Index: 366

Text #11

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.1419. Min Act: -0.0000

Data Index: 1316797 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1631031 (Python Code)

Max Activating Token Index: 606

Text #13

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1526550 (Python Code)

Max Activating Token Index: 534

Text #14

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.1306. Min Act: -0.0000

Data Index: 1558518 (Python Code)

Max Activating Token Index: 423

Text #15

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1628860 (Python Code)

Max Activating Token Index: 563

Text #16

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.1414. Min Act: -0.0000

Data Index: 121515 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.1242. Min Act: -0.0000

Data Index: 1481939 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1281551 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.1272. Min Act: -0.0000

Data Index: 1385629 (Python Code)

Max Activating Token Index: 727