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

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

Neuron 4617 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1169592 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1837. Min Act: -0.0000

Data Index: 1625099 (Python Code)

Max Activating Token Index: 818

Text #2

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1673. Min Act: -0.0000

Data Index: 1433780 (Python Code)

Max Activating Token Index: 790

Text #3

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1726. Min Act: -0.0000

Data Index: 284426 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1465. Min Act: -0.0000

Data Index: 1432711 (Python Code)

Max Activating Token Index: 535

Text #5

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1512. Min Act: -0.0000

Data Index: 185921 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1464. Min Act: -0.0001

Data Index: 1441808 (Python Code)

Max Activating Token Index: 489

Text #7

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1358. Min Act: -0.0000

Data Index: 1454274 (Python Code)

Max Activating Token Index: 186

Text #8

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1387. Min Act: -0.0000

Data Index: 1652303 (Python Code)

Max Activating Token Index: 805

Text #9

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1396. Min Act: -0.0000

Data Index: 1513559 (Python Code)

Max Activating Token Index: 747

Text #10

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1332. Min Act: -0.0000

Data Index: 1494846 (Python Code)

Max Activating Token Index: 990

Text #11

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1312. Min Act: -0.0000

Data Index: 1475981 (Python Code)

Max Activating Token Index: 956

Text #12

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1401. Min Act: -0.0000

Data Index: 1452742 (Python Code)

Max Activating Token Index: 939

Text #13

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1302. Min Act: -0.0000

Data Index: 885320 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1334. Min Act: -0.0001

Data Index: 1477549 (Python Code)

Max Activating Token Index: 353

Text #15

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1338. Min Act: -0.0000

Data Index: 716639 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1246. Min Act: -0.0000

Data Index: 219822 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1277. Min Act: -0.0000

Data Index: 1643585 (Python Code)

Max Activating Token Index: 997

Text #18

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1364. Min Act: -0.0000

Data Index: 742101 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1361796 (Python Code)

Max Activating Token Index: 990