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

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

Neuron 68 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0728. Min Act: -0.0002

Data Index: 291906 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1077515 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0594. Min Act: -0.0002

Data Index: 745418 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0588. Min Act: -0.0002

Data Index: 227913 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1354851 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1113200 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0486. Min Act: -0.0002

Data Index: 16465 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0489. Min Act: -0.0002

Data Index: 307696 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0468. Min Act: -0.0002

Data Index: 178849 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0498. Min Act: -0.0002

Data Index: 709487 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0476. Min Act: -0.0002

Data Index: 251199 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0477. Min Act: -0.0002

Data Index: 303591 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0477. Min Act: -0.0002

Data Index: 894867 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1115140 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0487. Min Act: -0.0002

Data Index: 200038 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0482. Min Act: -0.0002

Data Index: 909721 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0445. Min Act: -0.0002

Data Index: 986895 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0458. Min Act: -0.0002

Data Index: 304713 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0453. Min Act: -0.0002

Data Index: 844979 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1572370 (Python Code)

Max Activating Token Index: 960