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

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

Neuron 517 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: 1.8469. Min Range: -1.8469

Max Act: 1.8469. Min Act: -0.0000

Data Index: 920278 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 1.8469. Min Range: -1.8469

Max Act: 1.8360. Min Act: -0.0000

Data Index: 1273360 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 1.8469. Min Range: -1.8469

Max Act: 1.8346. Min Act: -0.0000

Data Index: 961172 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 1.8469. Min Range: -1.8469

Max Act: 1.6507. Min Act: -0.0000

Data Index: 1134012 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 1.8469. Min Range: -1.8469

Max Act: 1.4592. Min Act: -0.0000

Data Index: 839883 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 1.8469. Min Range: -1.8469

Max Act: 1.5860. Min Act: -0.0000

Data Index: 1047012 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 1.8469. Min Range: -1.8469

Max Act: 1.4765. Min Act: -0.0000

Data Index: 201218 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 1.8469. Min Range: -1.8469

Max Act: 1.2746. Min Act: -0.0000

Data Index: 889064 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 1.8469. Min Range: -1.8469

Max Act: 1.3280. Min Act: -0.0000

Data Index: 612242 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 1.8469. Min Range: -1.8469

Max Act: 1.3290. Min Act: -0.0000

Data Index: 484741 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 1.8469. Min Range: -1.8469

Max Act: 1.4130. Min Act: -0.0000

Data Index: 1061561 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 1.8469. Min Range: -1.8469

Max Act: 1.2444. Min Act: -0.0000

Data Index: 975653 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 1.8469. Min Range: -1.8469

Max Act: 1.3897. Min Act: -0.0000

Data Index: 498717 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 1.8469. Min Range: -1.8469

Max Act: 1.3120. Min Act: -0.0000

Data Index: 1225857 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 1.8469. Min Range: -1.8469

Max Act: 1.2871. Min Act: -0.0000

Data Index: 642618 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 1.8469. Min Range: -1.8469

Max Act: 1.2959. Min Act: -0.0000

Data Index: 832841 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 1.8469. Min Range: -1.8469

Max Act: 1.2079. Min Act: -0.0000

Data Index: 1023094 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 1.8469. Min Range: -1.8469

Max Act: 1.3415. Min Act: -0.0000

Data Index: 1282294 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 1.8469. Min Range: -1.8469

Max Act: 1.2738. Min Act: -0.0000

Data Index: 650861 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 1.8469. Min Range: -1.8469

Max Act: 1.2447. Min Act: -0.0000

Data Index: 361338 (C4 (Web Text))

Max Activating Token Index: 160