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

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

Neuron 5108 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1557. Min Act: -0.0002

Data Index: 749735 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1494. Min Act: -0.0002

Data Index: 308474 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1312. Min Act: -0.0002

Data Index: 766274 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1276. Min Act: -0.0002

Data Index: 100355 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1312. Min Act: -0.0002

Data Index: 834673 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1344. Min Act: -0.0002

Data Index: 444 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1438. Min Act: -0.0002

Data Index: 1004067 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1431. Min Act: -0.0002

Data Index: 778962 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1387. Min Act: -0.0002

Data Index: 295748 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1321. Min Act: -0.0002

Data Index: 290979 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1300. Min Act: -0.0002

Data Index: 934350 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1375. Min Act: -0.0002

Data Index: 238668 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1174. Min Act: -0.0002

Data Index: 1013919 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1352. Min Act: -0.0002

Data Index: 467757 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1311. Min Act: -0.0002

Data Index: 1174368 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1299. Min Act: -0.0002

Data Index: 475675 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1381. Min Act: -0.0002

Data Index: 421081 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1239. Min Act: -0.0002

Data Index: 811487 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1218. Min Act: -0.0002

Data Index: 610833 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1217. Min Act: -0.0002

Data Index: 946811 (C4 (Web Text))

Max Activating Token Index: 653