Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 831 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0460. Min Act: -0.0006

Data Index: 91870 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0443. Min Act: -0.0006

Data Index: 90492 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0429. Min Act: -0.0006

Data Index: 1181806 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0423. Min Act: -0.0006

Data Index: 133356 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0415. Min Act: -0.0006

Data Index: 980494 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0415. Min Act: -0.0006

Data Index: 138841 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0389. Min Act: -0.0006

Data Index: 1024947 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0386. Min Act: -0.0006

Data Index: 371493 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0406. Min Act: -0.0006

Data Index: 967190 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0404. Min Act: -0.0006

Data Index: 455014 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0412. Min Act: -0.0006

Data Index: 685661 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0387. Min Act: -0.0006

Data Index: 534321 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0383. Min Act: -0.0006

Data Index: 858469 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0386. Min Act: -0.0006

Data Index: 1094832 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0390. Min Act: -0.0006

Data Index: 633461 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0389. Min Act: -0.0006

Data Index: 355657 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0373. Min Act: -0.0006

Data Index: 567451 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0377. Min Act: -0.0006

Data Index: 971287 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0360. Min Act: -0.0006

Data Index: 699862 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0353. Min Act: -0.0006

Data Index: 444043 (C4 (Web Text))

Max Activating Token Index: 814