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

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

Neuron 1748 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1673. Min Act: -0.0000

Data Index: 1377475 (Python Code)

Max Activating Token Index: 277

Text #1

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1540335 (Python Code)

Max Activating Token Index: 489

Text #2

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1511. Min Act: -0.0000

Data Index: 1211763 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1577792 (Python Code)

Max Activating Token Index: 752

Text #4

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1543. Min Act: -0.0000

Data Index: 916848 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1335. Min Act: -0.0000

Data Index: 1618845 (Python Code)

Max Activating Token Index: 217

Text #6

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1416551 (Python Code)

Max Activating Token Index: 189

Text #7

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1457. Min Act: -0.0000

Data Index: 1523298 (Python Code)

Max Activating Token Index: 419

Text #8

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1437. Min Act: -0.0000

Data Index: 611489 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1193521 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1383. Min Act: -0.0000

Data Index: 172680 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1353. Min Act: -0.0000

Data Index: 1523213 (Python Code)

Max Activating Token Index: 375

Text #12

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1338. Min Act: -0.0000

Data Index: 1485176 (Python Code)

Max Activating Token Index: 314

Text #13

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1288. Min Act: -0.0000

Data Index: 251942 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1291. Min Act: -0.0000

Data Index: 1233561 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1487312 (Python Code)

Max Activating Token Index: 552

Text #16

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1320. Min Act: -0.0000

Data Index: 970366 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1240. Min Act: -0.0000

Data Index: 1250463 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1236. Min Act: -0.0000

Data Index: 1577304 (Python Code)

Max Activating Token Index: 449

Text #19

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1174. Min Act: -0.0000

Data Index: 480729 (C4 (Web Text))

Max Activating Token Index: 287