Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 437 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0438. Min Act: -0.0003

Data Index: 175906 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1171964 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0404. Min Act: -0.0003

Data Index: 110849 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0417. Min Act: -0.0003

Data Index: 887366 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0415. Min Act: -0.0004

Data Index: 744085 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0413. Min Act: -0.0003

Data Index: 452273 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1102234 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0401. Min Act: -0.0004

Data Index: 528912 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0421. Min Act: -0.0003

Data Index: 828625 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0421. Min Act: -0.0003

Data Index: 52065 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0389. Min Act: -0.0004

Data Index: 795434 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0407. Min Act: -0.0003

Data Index: 433810 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0404. Min Act: -0.0003

Data Index: 608134 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0402. Min Act: -0.0003

Data Index: 701680 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0389. Min Act: -0.0004

Data Index: 1198516 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0403. Min Act: -0.0003

Data Index: 1023055 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0388. Min Act: -0.0002

Data Index: 927429 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0392. Min Act: -0.0003

Data Index: 939593 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0396. Min Act: -0.0003

Data Index: 533202 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0402. Min Act: -0.0003

Data Index: 680306 (C4 (Web Text))

Max Activating Token Index: 463