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

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

Neuron 4205 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9440. Min Range: -3.9440

Max Act: 3.9440. Min Act: -0.0000

Data Index: 790387 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 3.9440. Min Range: -3.9440

Max Act: 3.4429. Min Act: -0.0000

Data Index: 523047 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 3.9440. Min Range: -3.9440

Max Act: 3.3160. Min Act: -0.0000

Data Index: 191435 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 3.9440. Min Range: -3.9440

Max Act: 3.0855. Min Act: -0.0000

Data Index: 95015 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 3.9440. Min Range: -3.9440

Max Act: 3.0299. Min Act: -0.0000

Data Index: 733254 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 3.9440. Min Range: -3.9440

Max Act: 2.9964. Min Act: -0.0000

Data Index: 1202842 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 3.9440. Min Range: -3.9440

Max Act: 3.0721. Min Act: -0.0000

Data Index: 644282 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 3.9440. Min Range: -3.9440

Max Act: 3.0712. Min Act: -0.0000

Data Index: 240481 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 3.9440. Min Range: -3.9440

Max Act: 2.9394. Min Act: -0.0000

Data Index: 868088 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 3.9440. Min Range: -3.9440

Max Act: 2.9493. Min Act: -0.0000

Data Index: 1043217 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 3.9440. Min Range: -3.9440

Max Act: 3.0657. Min Act: -0.0000

Data Index: 936071 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 3.9440. Min Range: -3.9440

Max Act: 2.9172. Min Act: -0.0000

Data Index: 622024 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 3.9440. Min Range: -3.9440

Max Act: 2.7530. Min Act: -0.0000

Data Index: 54824 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 3.9440. Min Range: -3.9440

Max Act: 2.8703. Min Act: -0.0000

Data Index: 673508 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 3.9440. Min Range: -3.9440

Max Act: 2.8905. Min Act: -0.0000

Data Index: 1010899 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 3.9440. Min Range: -3.9440

Max Act: 2.8716. Min Act: -0.0000

Data Index: 1050491 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 3.9440. Min Range: -3.9440

Max Act: 2.8421. Min Act: -0.0000

Data Index: 1264225 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 3.9440. Min Range: -3.9440

Max Act: 2.9838. Min Act: -0.0000

Data Index: 253856 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 3.9440. Min Range: -3.9440

Max Act: 2.8245. Min Act: -0.0000

Data Index: 99915 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 3.9440. Min Range: -3.9440

Max Act: 2.6909. Min Act: -0.0000

Data Index: 938286 (C4 (Web Text))

Max Activating Token Index: 856