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

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

Neuron 28 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.6412. Min Act: -0.0000

Data Index: 335070 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.5064. Min Act: -0.0000

Data Index: 711773 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1105162 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.4648. Min Act: -0.0000

Data Index: 431817 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.4723. Min Act: -0.0000

Data Index: 584087 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.4375. Min Act: -0.0000

Data Index: 714351 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.4253. Min Act: -0.0000

Data Index: 403019 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.4252. Min Act: -0.0000

Data Index: 275774 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.4238. Min Act: -0.0000

Data Index: 789728 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.4284. Min Act: -0.0000

Data Index: 171742 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1320147 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.3753. Min Act: -0.0000

Data Index: 1140328 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.3683. Min Act: -0.0000

Data Index: 1263442 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.3737. Min Act: -0.0000

Data Index: 626158 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.3970. Min Act: -0.0000

Data Index: 1009134 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.3510. Min Act: -0.0000

Data Index: 265591 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1279824 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.3527. Min Act: -0.0000

Data Index: 50717 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.3598. Min Act: -0.0000

Data Index: 939827 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.6412. Min Range: -0.6412

Max Act: 0.3056. Min Act: -0.0000

Data Index: 371949 (C4 (Web Text))

Max Activating Token Index: 625