Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1150 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1522. Min Act: -0.0001

Data Index: 926118 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1405. Min Act: -0.0001

Data Index: 538866 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1327. Min Act: -0.0001

Data Index: 1101414 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1205. Min Act: -0.0001

Data Index: 95750 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1198. Min Act: -0.0001

Data Index: 1186924 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1281. Min Act: -0.0001

Data Index: 1344216 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1290. Min Act: -0.0001

Data Index: 1038780 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1272. Min Act: -0.0001

Data Index: 14818 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1260. Min Act: -0.0001

Data Index: 603915 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1209. Min Act: -0.0001

Data Index: 436562 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1204. Min Act: -0.0001

Data Index: 408630 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1257. Min Act: -0.0001

Data Index: 130526 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1282. Min Act: -0.0001

Data Index: 1336306 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1351346 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1182. Min Act: -0.0001

Data Index: 945195 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1259. Min Act: -0.0001

Data Index: 656211 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1212. Min Act: -0.0001

Data Index: 1201129 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1255. Min Act: -0.0001

Data Index: 613520 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1212. Min Act: -0.0001

Data Index: 587745 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1120. Min Act: -0.0001

Data Index: 529429 (C4 (Web Text))

Max Activating Token Index: 592