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

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

Neuron 5427 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: 0.1386. Min Range: -0.1386

Max Act: 0.1386. Min Act: -0.0002

Data Index: 751228 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1377. Min Act: -0.0002

Data Index: 834901 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1337. Min Act: -0.0002

Data Index: 1134531 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1286. Min Act: -0.0002

Data Index: 1124458 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1332. Min Act: -0.0002

Data Index: 1064592 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1314. Min Act: -0.0002

Data Index: 1013397 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1273. Min Act: -0.0002

Data Index: 243783 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1259. Min Act: -0.0002

Data Index: 709884 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1298. Min Act: -0.0002

Data Index: 433762 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1257. Min Act: -0.0002

Data Index: 1026133 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1236. Min Act: -0.0002

Data Index: 1284012 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1245. Min Act: -0.0002

Data Index: 847736 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1199. Min Act: -0.0002

Data Index: 934513 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1223. Min Act: -0.0002

Data Index: 715526 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1233. Min Act: -0.0002

Data Index: 81329 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1222. Min Act: -0.0002

Data Index: 244745 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1229. Min Act: -0.0002

Data Index: 495001 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1214. Min Act: -0.0003

Data Index: 1305738 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1201. Min Act: -0.0002

Data Index: 670205 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1203. Min Act: -0.0002

Data Index: 588243 (C4 (Web Text))

Max Activating Token Index: 39