Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4805 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1643. Min Act: -0.0000

Data Index: 931366 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1644. Min Act: -0.0000

Data Index: 1088223 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1647. Min Act: -0.0000

Data Index: 982305 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1513. Min Act: -0.0001

Data Index: 508501 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1508. Min Act: -0.0001

Data Index: 1201106 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1400. Min Act: -0.0001

Data Index: 772644 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1269. Min Act: -0.0001

Data Index: 1195520 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1344. Min Act: -0.0000

Data Index: 1038440 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1386. Min Act: -0.0001

Data Index: 413499 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1383. Min Act: -0.0001

Data Index: 233716 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1366. Min Act: -0.0001

Data Index: 1214680 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1348. Min Act: -0.0000

Data Index: 931601 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1424. Min Act: -0.0001

Data Index: 1288817 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1577. Min Act: -0.0001

Data Index: 1309410 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1185. Min Act: -0.0001

Data Index: 750840 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1320. Min Act: -0.0001

Data Index: 272237 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1225. Min Act: -0.0001

Data Index: 481995 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1285. Min Act: -0.0000

Data Index: 131239 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1238. Min Act: -0.0001

Data Index: 213923 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1324. Min Act: -0.0001

Data Index: 215499 (C4 (Web Text))

Max Activating Token Index: 477