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

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

Neuron 409 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: 0.0636. Min Range: -0.0636

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1245621 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0515. Min Act: -0.0002

Data Index: 231067 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0533. Min Act: -0.0002

Data Index: 900701 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0502. Min Act: -0.0002

Data Index: 455875 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1126695 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1060196 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1282119 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1035923 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1158281 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1324009 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0431. Min Act: -0.0002

Data Index: 897087 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0428. Min Act: -0.0002

Data Index: 217156 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0417. Min Act: -0.0002

Data Index: 15293 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0422. Min Act: -0.0002

Data Index: 164826 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1268317 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0416. Min Act: -0.0002

Data Index: 168391 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0408. Min Act: -0.0002

Data Index: 178137 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0404. Min Act: -0.0002

Data Index: 478895 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1271579 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1148465 (C4 (Web Text))

Max Activating Token Index: 323