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

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

Neuron 5225 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1721. Min Act: -0.0002

Data Index: 1456236 (Python Code)

Max Activating Token Index: 34

Text #1

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1539. Min Act: -0.0002

Data Index: 1489321 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1506. Min Act: -0.0002

Data Index: 456210 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1469. Min Act: -0.0002

Data Index: 353178 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1386. Min Act: -0.0002

Data Index: 1626201 (Python Code)

Max Activating Token Index: 227

Text #5

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1368. Min Act: -0.0002

Data Index: 1448826 (Python Code)

Max Activating Token Index: 616

Text #6

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1355. Min Act: -0.0002

Data Index: 1644387 (Python Code)

Max Activating Token Index: 680

Text #7

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1328. Min Act: -0.0002

Data Index: 673374 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1356. Min Act: -0.0002

Data Index: 1572041 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1349. Min Act: -0.0002

Data Index: 1518155 (Python Code)

Max Activating Token Index: 826

Text #10

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1354. Min Act: -0.0002

Data Index: 1242237 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1330. Min Act: -0.0002

Data Index: 768756 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1334. Min Act: -0.0002

Data Index: 1622982 (Python Code)

Max Activating Token Index: 886

Text #13

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1334. Min Act: -0.0002

Data Index: 1533019 (Python Code)

Max Activating Token Index: 808

Text #14

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1306. Min Act: -0.0002

Data Index: 1532370 (Python Code)

Max Activating Token Index: 640

Text #15

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1286. Min Act: -0.0002

Data Index: 1457935 (Python Code)

Max Activating Token Index: 2

Text #16

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1285. Min Act: -0.0002

Data Index: 1274419 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1304. Min Act: -0.0002

Data Index: 1503566 (Python Code)

Max Activating Token Index: 223

Text #18

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1268. Min Act: -0.0002

Data Index: 1437017 (Python Code)

Max Activating Token Index: 55

Text #19

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1289. Min Act: -0.0002

Data Index: 727754 (C4 (Web Text))

Max Activating Token Index: 559