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

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

Neuron 1823 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9733. Min Range: -4.9733

Max Act: 4.6493. Min Act: -0.0000

Data Index: 1530674 (Python Code)

Max Activating Token Index: 361

Text #1

Max Range: 4.9733. Min Range: -4.9733

Max Act: 4.8768. Min Act: -0.0000

Data Index: 1443482 (Python Code)

Max Activating Token Index: 58

Text #2

Max Range: 4.9733. Min Range: -4.9733

Max Act: 4.6796. Min Act: -0.0000

Data Index: 1562443 (Python Code)

Max Activating Token Index: 259

Text #3

Max Range: 4.9733. Min Range: -4.9733

Max Act: 4.9733. Min Act: -0.0000

Data Index: 1603859 (Python Code)

Max Activating Token Index: 936

Text #4

Max Range: 4.9733. Min Range: -4.9733

Max Act: 4.6874. Min Act: -0.0000

Data Index: 1367224 (Python Code)

Max Activating Token Index: 149

Text #5

Max Range: 4.9733. Min Range: -4.9733

Max Act: 4.3980. Min Act: -0.0000

Data Index: 1478736 (Python Code)

Max Activating Token Index: 988

Text #6

Max Range: 4.9733. Min Range: -4.9733

Max Act: 4.7101. Min Act: -0.0000

Data Index: 1499533 (Python Code)

Max Activating Token Index: 284

Text #7

Max Range: 4.9733. Min Range: -4.9733

Max Act: 4.2946. Min Act: -0.0000

Data Index: 1546800 (Python Code)

Max Activating Token Index: 257

Text #8

Max Range: 4.9733. Min Range: -4.9733

Max Act: 4.2414. Min Act: -0.0000

Data Index: 1551843 (Python Code)

Max Activating Token Index: 308

Text #9

Max Range: 4.9733. Min Range: -4.9733

Max Act: 4.2402. Min Act: -0.0000

Data Index: 471611 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 4.9733. Min Range: -4.9733

Max Act: 4.2684. Min Act: -0.0000

Data Index: 1465172 (Python Code)

Max Activating Token Index: 670

Text #11

Max Range: 4.9733. Min Range: -4.9733

Max Act: 4.3855. Min Act: -0.0000

Data Index: 857292 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 4.9733. Min Range: -4.9733

Max Act: 4.5645. Min Act: -0.0000

Data Index: 1515223 (Python Code)

Max Activating Token Index: 1011

Text #13

Max Range: 4.9733. Min Range: -4.9733

Max Act: 4.1052. Min Act: -0.0000

Data Index: 807266 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 4.9733. Min Range: -4.9733

Max Act: 4.4041. Min Act: -0.0000

Data Index: 555404 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 4.9733. Min Range: -4.9733

Max Act: 4.1269. Min Act: -0.0000

Data Index: 1036153 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 4.9733. Min Range: -4.9733

Max Act: 4.1311. Min Act: -0.0000

Data Index: 519618 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 4.9733. Min Range: -4.9733

Max Act: 3.9507. Min Act: -0.0000

Data Index: 1528215 (Python Code)

Max Activating Token Index: 919

Text #18

Max Range: 4.9733. Min Range: -4.9733

Max Act: 3.7903. Min Act: -0.0000

Data Index: 730587 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 4.9733. Min Range: -4.9733

Max Act: 3.9328. Min Act: -0.0000

Data Index: 1555625 (Python Code)

Max Activating Token Index: 568