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

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

Neuron 3708 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: 0.1483. Min Range: -0.1483

Max Act: 0.1483. Min Act: -0.0003

Data Index: 1317024 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1370. Min Act: -0.0002

Data Index: 1341953 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1372. Min Act: -0.0002

Data Index: 279861 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1386. Min Act: -0.0002

Data Index: 398036 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1338. Min Act: -0.0002

Data Index: 1077407 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1337. Min Act: -0.0002

Data Index: 834592 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1326. Min Act: -0.0002

Data Index: 932637 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1311. Min Act: -0.0002

Data Index: 1142131 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1329. Min Act: -0.0002

Data Index: 1224358 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1301. Min Act: -0.0002

Data Index: 1246462 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1288. Min Act: -0.0002

Data Index: 1270430 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1290. Min Act: -0.0002

Data Index: 1298985 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1302. Min Act: -0.0002

Data Index: 251299 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1290. Min Act: -0.0002

Data Index: 564313 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1282. Min Act: -0.0002

Data Index: 255464 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1293. Min Act: -0.0003

Data Index: 229204 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1262. Min Act: -0.0002

Data Index: 926886 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1257. Min Act: -0.0002

Data Index: 529252 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1276. Min Act: -0.0002

Data Index: 18767 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1246. Min Act: -0.0002

Data Index: 269439 (C4 (Web Text))

Max Activating Token Index: 781