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

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

Neuron 5739 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: 0.1321. Min Range: -0.1321

Max Act: 0.1321. Min Act: -0.0002

Data Index: 1023890 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1311. Min Act: -0.0002

Data Index: 37798 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1297. Min Act: -0.0002

Data Index: 1165106 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1287. Min Act: -0.0002

Data Index: 1064334 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1285. Min Act: -0.0002

Data Index: 151939 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1268. Min Act: -0.0002

Data Index: 578539 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1225. Min Act: -0.0002

Data Index: 490118 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1285. Min Act: -0.0002

Data Index: 19880 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1231. Min Act: -0.0002

Data Index: 592716 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1269. Min Act: -0.0002

Data Index: 1201437 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1228. Min Act: -0.0002

Data Index: 1134935 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1231. Min Act: -0.0002

Data Index: 890175 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1254. Min Act: -0.0002

Data Index: 325259 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1254. Min Act: -0.0002

Data Index: 843473 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1234. Min Act: -0.0002

Data Index: 1050768 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1231. Min Act: -0.0002

Data Index: 608357 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1257. Min Act: -0.0002

Data Index: 1159818 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1234. Min Act: -0.0002

Data Index: 213414 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1233. Min Act: -0.0002

Data Index: 378137 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1200. Min Act: -0.0002

Data Index: 976689 (C4 (Web Text))

Max Activating Token Index: 133