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

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

Neuron 5514 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: 1.4021. Min Range: -1.4021

Max Act: 1.4021. Min Act: -0.0002

Data Index: 1484551 (Python Code)

Max Activating Token Index: 1011

Text #1

Max Range: 1.4021. Min Range: -1.4021

Max Act: 1.3417. Min Act: -0.0002

Data Index: 1633121 (Python Code)

Max Activating Token Index: 1014

Text #2

Max Range: 1.4021. Min Range: -1.4021

Max Act: 1.2408. Min Act: -0.0002

Data Index: 1502964 (Python Code)

Max Activating Token Index: 962

Text #3

Max Range: 1.4021. Min Range: -1.4021

Max Act: 1.2436. Min Act: -0.0002

Data Index: 1520409 (Python Code)

Max Activating Token Index: 171

Text #4

Max Range: 1.4021. Min Range: -1.4021

Max Act: 1.2309. Min Act: -0.0002

Data Index: 1512794 (Python Code)

Max Activating Token Index: 969

Text #5

Max Range: 1.4021. Min Range: -1.4021

Max Act: 1.1975. Min Act: -0.0002

Data Index: 1463340 (Python Code)

Max Activating Token Index: 847

Text #6

Max Range: 1.4021. Min Range: -1.4021

Max Act: 1.1917. Min Act: -0.0002

Data Index: 1441970 (Python Code)

Max Activating Token Index: 817

Text #7

Max Range: 1.4021. Min Range: -1.4021

Max Act: 1.1850. Min Act: -0.0002

Data Index: 1640563 (Python Code)

Max Activating Token Index: 885

Text #8

Max Range: 1.4021. Min Range: -1.4021

Max Act: 1.1560. Min Act: -0.0002

Data Index: 1369949 (Python Code)

Max Activating Token Index: 817

Text #9

Max Range: 1.4021. Min Range: -1.4021

Max Act: 1.1528. Min Act: -0.0002

Data Index: 1468625 (Python Code)

Max Activating Token Index: 692

Text #10

Max Range: 1.4021. Min Range: -1.4021

Max Act: 1.1284. Min Act: -0.0002

Data Index: 1367513 (Python Code)

Max Activating Token Index: 71

Text #11

Max Range: 1.4021. Min Range: -1.4021

Max Act: 1.1334. Min Act: -0.0002

Data Index: 1455875 (Python Code)

Max Activating Token Index: 780

Text #12

Max Range: 1.4021. Min Range: -1.4021

Max Act: 1.1306. Min Act: -0.0002

Data Index: 1429166 (Python Code)

Max Activating Token Index: 441

Text #13

Max Range: 1.4021. Min Range: -1.4021

Max Act: 1.1533. Min Act: -0.0002

Data Index: 1377448 (Python Code)

Max Activating Token Index: 642

Text #14

Max Range: 1.4021. Min Range: -1.4021

Max Act: 1.1458. Min Act: -0.0002

Data Index: 1433788 (Python Code)

Max Activating Token Index: 46

Text #15

Max Range: 1.4021. Min Range: -1.4021

Max Act: 1.1267. Min Act: -0.0002

Data Index: 1386576 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 1.4021. Min Range: -1.4021

Max Act: 1.1361. Min Act: -0.0002

Data Index: 1608169 (Python Code)

Max Activating Token Index: 81

Text #17

Max Range: 1.4021. Min Range: -1.4021

Max Act: 1.1365. Min Act: -0.0002

Data Index: 160836 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 1.4021. Min Range: -1.4021

Max Act: 1.1512. Min Act: -0.0002

Data Index: 1505319 (Python Code)

Max Activating Token Index: 40

Text #19

Max Range: 1.4021. Min Range: -1.4021

Max Act: 1.1101. Min Act: -0.0002

Data Index: 1404650 (Python Code)

Max Activating Token Index: 875