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

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

Neuron 4604 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.7360. Min Act: -0.0000

Data Index: 231255 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.6179. Min Act: -0.0000

Data Index: 583867 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.6223. Min Act: -0.0000

Data Index: 1198444 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.6587. Min Act: -0.0000

Data Index: 299702 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5923. Min Act: -0.0000

Data Index: 25380 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5701. Min Act: -0.0000

Data Index: 703203 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5601. Min Act: -0.0000

Data Index: 359398 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5427. Min Act: -0.0000

Data Index: 828194 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5667. Min Act: -0.0000

Data Index: 931894 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1293556 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1223377 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.4819. Min Act: -0.0000

Data Index: 580625 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.4918. Min Act: -0.0000

Data Index: 230123 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5045. Min Act: -0.0000

Data Index: 995581 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.4858. Min Act: -0.0000

Data Index: 1093103 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.4939. Min Act: -0.0000

Data Index: 811826 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.4771. Min Act: -0.0000

Data Index: 150042 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.4793. Min Act: -0.0000

Data Index: 911557 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.4561. Min Act: -0.0000

Data Index: 418783 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.4665. Min Act: -0.0000

Data Index: 938413 (C4 (Web Text))

Max Activating Token Index: 511