Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3239 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0507. Min Act: -0.0003

Data Index: 411376 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0428. Min Act: -0.0003

Data Index: 161192 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0400. Min Act: -0.0003

Data Index: 848724 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0346. Min Act: -0.0003

Data Index: 986793 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0382. Min Act: -0.0003

Data Index: 911444 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0365. Min Act: -0.0003

Data Index: 646100 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0282. Min Act: -0.0003

Data Index: 235200 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1047065 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0332. Min Act: -0.0003

Data Index: 1282986 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0358. Min Act: -0.0003

Data Index: 357253 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0352. Min Act: -0.0003

Data Index: 1270313 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0338. Min Act: -0.0003

Data Index: 903778 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0357. Min Act: -0.0003

Data Index: 697851 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0359. Min Act: -0.0003

Data Index: 248508 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0357. Min Act: -0.0003

Data Index: 788783 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0356. Min Act: -0.0003

Data Index: 782629 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0341. Min Act: -0.0003

Data Index: 776958 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0334. Min Act: -0.0003

Data Index: 472228 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1292713 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0342. Min Act: -0.0003

Data Index: 39659 (C4 (Web Text))

Max Activating Token Index: 90