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

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

Neuron 1610 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: 0.0412. Min Range: -0.0412

Max Act: 0.0409. Min Act: -0.0006

Data Index: 699034 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0410. Min Act: -0.0006

Data Index: 152415 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0391. Min Act: -0.0006

Data Index: 1197472 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0374. Min Act: -0.0006

Data Index: 235524 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0405. Min Act: -0.0006

Data Index: 517436 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0396. Min Act: -0.0006

Data Index: 899663 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0358. Min Act: -0.0006

Data Index: 1059909 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0412. Min Act: -0.0006

Data Index: 364286 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0385. Min Act: -0.0006

Data Index: 883788 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0398. Min Act: -0.0006

Data Index: 357069 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0376. Min Act: -0.0006

Data Index: 933015 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0390. Min Act: -0.0006

Data Index: 1317285 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0366. Min Act: -0.0006

Data Index: 28016 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0380. Min Act: -0.0006

Data Index: 522301 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0378. Min Act: -0.0006

Data Index: 479291 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0377. Min Act: -0.0006

Data Index: 443925 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0384. Min Act: -0.0006

Data Index: 442019 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0365. Min Act: -0.0006

Data Index: 443565 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0367. Min Act: -0.0006

Data Index: 285587 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0390. Min Act: -0.0006

Data Index: 244159 (C4 (Web Text))

Max Activating Token Index: 1007