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

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

Neuron 2100 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5982. Min Act: -0.0001

Data Index: 1334508 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.6346. Min Act: -0.0000

Data Index: 421478 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5990. Min Act: -0.0000

Data Index: 612278 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5571. Min Act: -0.0000

Data Index: 795641 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5552. Min Act: -0.0000

Data Index: 73697 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5439. Min Act: -0.0000

Data Index: 1111926 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5166. Min Act: -0.0000

Data Index: 31121 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5338. Min Act: -0.0001

Data Index: 608790 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1073632 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5327. Min Act: -0.0000

Data Index: 555022 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5274. Min Act: -0.0000

Data Index: 1117609 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5251. Min Act: -0.0001

Data Index: 539702 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5274. Min Act: -0.0000

Data Index: 618203 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5404. Min Act: -0.0001

Data Index: 147112 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5221. Min Act: -0.0000

Data Index: 8282 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5202. Min Act: -0.0000

Data Index: 989760 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4953. Min Act: -0.0000

Data Index: 635772 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4904. Min Act: -0.0001

Data Index: 1202568 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1242837 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4719. Min Act: -0.0001

Data Index: 1238689 (C4 (Web Text))

Max Activating Token Index: 698