Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 484 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.6196. Min Act: -0.0000

Data Index: 540750 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.5649. Min Act: -0.0000

Data Index: 411964 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.5442. Min Act: -0.0000

Data Index: 265045 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.5028. Min Act: -0.0000

Data Index: 707162 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4958. Min Act: -0.0000

Data Index: 990364 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4686. Min Act: -0.0000

Data Index: 422498 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4677. Min Act: -0.0000

Data Index: 9318 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4502. Min Act: -0.0000

Data Index: 518479 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4740. Min Act: -0.0000

Data Index: 636827 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4889. Min Act: -0.0000

Data Index: 382652 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4412. Min Act: -0.0000

Data Index: 887591 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4738. Min Act: -0.0000

Data Index: 343882 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4464. Min Act: -0.0000

Data Index: 459308 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4437. Min Act: -0.0000

Data Index: 1163538 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4459. Min Act: -0.0000

Data Index: 279922 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4271. Min Act: -0.0000

Data Index: 319894 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1725 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4430. Min Act: -0.0000

Data Index: 1329 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4385. Min Act: -0.0000

Data Index: 852706 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4315. Min Act: -0.0000

Data Index: 422239 (C4 (Web Text))

Max Activating Token Index: 764