Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 149 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1680. Min Act: -0.0002

Data Index: 968656 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1395. Min Act: -0.0002

Data Index: 16093 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1513. Min Act: -0.0002

Data Index: 628713 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1519. Min Act: -0.0002

Data Index: 604362 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1455. Min Act: -0.0002

Data Index: 734596 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1488. Min Act: -0.0002

Data Index: 1124871 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1397. Min Act: -0.0002

Data Index: 1178447 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1473. Min Act: -0.0002

Data Index: 1136087 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1402. Min Act: -0.0002

Data Index: 1300925 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1407. Min Act: -0.0002

Data Index: 226836 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1283. Min Act: -0.0002

Data Index: 153631 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1365. Min Act: -0.0002

Data Index: 414824 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1302. Min Act: -0.0002

Data Index: 273064 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1270. Min Act: -0.0002

Data Index: 60067 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1281. Min Act: -0.0002

Data Index: 709076 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1346. Min Act: -0.0002

Data Index: 136463 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1309. Min Act: -0.0002

Data Index: 696389 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1382. Min Act: -0.0002

Data Index: 767196 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1240. Min Act: -0.0002

Data Index: 987036 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1335. Min Act: -0.0002

Data Index: 537485 (C4 (Web Text))

Max Activating Token Index: 902