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

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

Neuron 4625 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: 0.1666. Min Range: -0.1666

Max Act: 0.1666. Min Act: -0.0002

Data Index: 1370700 (Python Code)

Max Activating Token Index: 235

Text #1

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1457. Min Act: -0.0002

Data Index: 1560319 (Python Code)

Max Activating Token Index: 315

Text #2

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1443. Min Act: -0.0002

Data Index: 1643993 (Python Code)

Max Activating Token Index: 598

Text #3

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1497. Min Act: -0.0002

Data Index: 1393572 (Python Code)

Max Activating Token Index: 112

Text #4

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1431. Min Act: -0.0002

Data Index: 1555834 (Python Code)

Max Activating Token Index: 711

Text #5

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1389. Min Act: -0.0002

Data Index: 1431581 (Python Code)

Max Activating Token Index: 267

Text #6

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1412. Min Act: -0.0002

Data Index: 1453495 (Python Code)

Max Activating Token Index: 769

Text #7

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1369. Min Act: -0.0002

Data Index: 1366504 (Python Code)

Max Activating Token Index: 230

Text #8

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1356. Min Act: -0.0002

Data Index: 1640490 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1332. Min Act: -0.0002

Data Index: 1558315 (Python Code)

Max Activating Token Index: 27

Text #10

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1356. Min Act: -0.0002

Data Index: 1522234 (Python Code)

Max Activating Token Index: 220

Text #11

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1318. Min Act: -0.0002

Data Index: 1623797 (Python Code)

Max Activating Token Index: 699

Text #12

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1326. Min Act: -0.0002

Data Index: 1543004 (Python Code)

Max Activating Token Index: 962

Text #13

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1320. Min Act: -0.0002

Data Index: 1452044 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1309. Min Act: -0.0002

Data Index: 1434822 (Python Code)

Max Activating Token Index: 582

Text #15

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1292. Min Act: -0.0002

Data Index: 1576354 (Python Code)

Max Activating Token Index: 487

Text #16

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1280. Min Act: -0.0002

Data Index: 1565113 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1273. Min Act: -0.0002

Data Index: 1437256 (Python Code)

Max Activating Token Index: 154

Text #18

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1291. Min Act: -0.0002

Data Index: 1424011 (Python Code)

Max Activating Token Index: 246

Text #19

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1270. Min Act: -0.0002

Data Index: 1452796 (Python Code)

Max Activating Token Index: 79