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

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

Neuron 3155 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.6395. Min Act: -0.0000

Data Index: 1324558 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.7526. Min Act: -0.0000

Data Index: 640388 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.2463. Min Act: -0.0000

Data Index: 267503 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.0256. Min Act: -0.0000

Data Index: 1315370 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.1476. Min Act: -0.0000

Data Index: 687034 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 4.7526. Min Range: -4.7526

Max Act: 3.7819. Min Act: -0.0000

Data Index: 1039011 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 4.7526. Min Range: -4.7526

Max Act: 3.9954. Min Act: -0.0000

Data Index: 303099 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 4.7526. Min Range: -4.7526

Max Act: 3.7975. Min Act: -0.0000

Data Index: 14427 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 4.7526. Min Range: -4.7526

Max Act: 3.8848. Min Act: -0.0000

Data Index: 324720 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 4.7526. Min Range: -4.7526

Max Act: 3.8284. Min Act: -0.0000

Data Index: 54803 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 4.7526. Min Range: -4.7526

Max Act: 3.6362. Min Act: -0.0000

Data Index: 325788 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 4.7526. Min Range: -4.7526

Max Act: 3.7958. Min Act: -0.0000

Data Index: 539348 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 4.7526. Min Range: -4.7526

Max Act: 3.2790. Min Act: -0.0000

Data Index: 485509 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 4.7526. Min Range: -4.7526

Max Act: 3.5078. Min Act: -0.0000

Data Index: 375857 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 4.7526. Min Range: -4.7526

Max Act: 3.3701. Min Act: -0.0000

Data Index: 1150371 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 4.7526. Min Range: -4.7526

Max Act: 3.7394. Min Act: -0.0000

Data Index: 935469 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 4.7526. Min Range: -4.7526

Max Act: 3.5218. Min Act: -0.0000

Data Index: 670892 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 4.7526. Min Range: -4.7526

Max Act: 3.3603. Min Act: -0.0000

Data Index: 1087508 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 4.7526. Min Range: -4.7526

Max Act: 3.1952. Min Act: -0.0000

Data Index: 600009 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 4.7526. Min Range: -4.7526

Max Act: 3.1435. Min Act: -0.0000

Data Index: 200401 (C4 (Web Text))

Max Activating Token Index: 784