Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2720 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1508. Min Act: -0.0001

Data Index: 637866 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1499. Min Act: -0.0000

Data Index: 117467 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1371. Min Act: -0.0001

Data Index: 129522 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1400. Min Act: -0.0000

Data Index: 814803 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1294. Min Act: -0.0001

Data Index: 700450 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1222. Min Act: -0.0001

Data Index: 1288007 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1222. Min Act: -0.0000

Data Index: 224 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1206. Min Act: -0.0000

Data Index: 422562 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1259. Min Act: -0.0001

Data Index: 268208 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1203. Min Act: -0.0000

Data Index: 642913 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1240. Min Act: -0.0000

Data Index: 338299 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1330234 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1212. Min Act: -0.0000

Data Index: 161204 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1195. Min Act: -0.0000

Data Index: 32900 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1192. Min Act: -0.0001

Data Index: 397016 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1147. Min Act: -0.0001

Data Index: 687179 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1000925 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1181. Min Act: -0.0000

Data Index: 753966 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1171. Min Act: -0.0001

Data Index: 659858 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1204. Min Act: -0.0001

Data Index: 732114 (C4 (Web Text))

Max Activating Token Index: 873