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

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

Neuron 799 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: 0.0421. Min Range: -0.0421

Max Act: 0.0421. Min Act: -0.0006

Data Index: 384382 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0408. Min Act: -0.0006

Data Index: 827814 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0409. Min Act: -0.0006

Data Index: 1184202 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0379. Min Act: -0.0006

Data Index: 1257034 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0383. Min Act: -0.0006

Data Index: 500418 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0375. Min Act: -0.0006

Data Index: 555756 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0379. Min Act: -0.0006

Data Index: 803767 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0356. Min Act: -0.0006

Data Index: 1294991 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0335. Min Act: -0.0006

Data Index: 619133 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0355. Min Act: -0.0006

Data Index: 31441 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0364. Min Act: -0.0006

Data Index: 750827 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0359. Min Act: -0.0006

Data Index: 413302 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0371. Min Act: -0.0006

Data Index: 1173756 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0369. Min Act: -0.0006

Data Index: 726365 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0367. Min Act: -0.0006

Data Index: 639869 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0375. Min Act: -0.0006

Data Index: 398091 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0353. Min Act: -0.0006

Data Index: 160316 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0363. Min Act: -0.0006

Data Index: 285546 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0350. Min Act: -0.0006

Data Index: 1449565 (Python Code)

Max Activating Token Index: 419

Text #19

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0358. Min Act: -0.0006

Data Index: 1327957 (C4 (Web Text))

Max Activating Token Index: 595