Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3729 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.6037. Min Act: -0.0001

Data Index: 1223866 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.6443. Min Act: -0.0001

Data Index: 756385 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.5971. Min Act: -0.0001

Data Index: 251312 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.6286. Min Act: -0.0000

Data Index: 853651 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.5361. Min Act: -0.0001

Data Index: 736982 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.5580. Min Act: -0.0001

Data Index: 624584 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.5672. Min Act: -0.0001

Data Index: 463257 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.5982. Min Act: -0.0001

Data Index: 995184 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.5244. Min Act: -0.0001

Data Index: 1139647 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.5348. Min Act: -0.0001

Data Index: 301362 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.5723. Min Act: -0.0001

Data Index: 1023336 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.4836. Min Act: -0.0001

Data Index: 751488 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.4831. Min Act: -0.0001

Data Index: 783813 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.5464. Min Act: -0.0001

Data Index: 305460 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.4563. Min Act: -0.0001

Data Index: 222624 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.5750. Min Act: -0.0001

Data Index: 145233 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.5297. Min Act: -0.0000

Data Index: 525264 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.4060. Min Act: -0.0001

Data Index: 941923 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.5012. Min Act: -0.0001

Data Index: 296873 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 1.6443. Min Range: -1.6443

Max Act: 1.4386. Min Act: -0.0001

Data Index: 978846 (C4 (Web Text))

Max Activating Token Index: 859