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

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

Neuron 3440 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.8604. Min Act: -0.0000

Data Index: 827356 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.5201. Min Act: -0.0000

Data Index: 1452646 (Python Code)

Max Activating Token Index: 903

Text #2

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.4389. Min Act: -0.0000

Data Index: 37642 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.4294. Min Act: -0.0000

Data Index: 290061 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.4795. Min Act: -0.0000

Data Index: 1238995 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.4731. Min Act: -0.0000

Data Index: 1328387 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.4649. Min Act: -0.0000

Data Index: 480668 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.4679. Min Act: -0.0000

Data Index: 332879 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.4160. Min Act: -0.0000

Data Index: 1496684 (Python Code)

Max Activating Token Index: 154

Text #9

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.4556. Min Act: -0.0000

Data Index: 160301 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.4450. Min Act: -0.0000

Data Index: 531178 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.5390. Min Act: -0.0000

Data Index: 727187 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.3413. Min Act: -0.0000

Data Index: 1640623 (Python Code)

Max Activating Token Index: 206

Text #13

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.4104. Min Act: -0.0000

Data Index: 1355149 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.4404. Min Act: -0.0000

Data Index: 432038 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.3609. Min Act: -0.0000

Data Index: 1017567 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.3428. Min Act: -0.0000

Data Index: 793422 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.3409. Min Act: -0.0000

Data Index: 240022 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.3114. Min Act: -0.0000

Data Index: 620236 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 1.8604. Min Range: -1.8604

Max Act: 1.2303. Min Act: -0.0000

Data Index: 536076 (C4 (Web Text))

Max Activating Token Index: 268