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

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

Neuron 39 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.5300. Min Act: -0.0003

Data Index: 20865 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.5422. Min Act: -0.0003

Data Index: 1324385 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.5223. Min Act: -0.0003

Data Index: 103644 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.5303. Min Act: -0.0003

Data Index: 941914 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.5287. Min Act: -0.0003

Data Index: 170916 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.5104. Min Act: -0.0003

Data Index: 706623 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.5382. Min Act: -0.0003

Data Index: 1283003 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.5181. Min Act: -0.0003

Data Index: 303933 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4956. Min Act: -0.0003

Data Index: 950239 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4984. Min Act: -0.0003

Data Index: 862762 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4812. Min Act: -0.0003

Data Index: 351877 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4968. Min Act: -0.0003

Data Index: 148377 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4929. Min Act: -0.0003

Data Index: 818044 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4756. Min Act: -0.0003

Data Index: 1280252 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4684. Min Act: -0.0003

Data Index: 526610 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4786. Min Act: -0.0003

Data Index: 1171986 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4677. Min Act: -0.0003

Data Index: 578503 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4814. Min Act: -0.0003

Data Index: 1275737 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4796. Min Act: -0.0003

Data Index: 1346705 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4655. Min Act: -0.0003

Data Index: 118502 (C4 (Web Text))

Max Activating Token Index: 72