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

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

Neuron 119 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0866. Min Act: -0.0002

Data Index: 24241 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1565938 (Python Code)

Max Activating Token Index: 351

Text #2

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1410077 (Python Code)

Max Activating Token Index: 331

Text #3

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1474215 (Python Code)

Max Activating Token Index: 444

Text #4

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0509. Min Act: -0.0002

Data Index: 816773 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1634272 (Python Code)

Max Activating Token Index: 1016

Text #6

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1361109 (Python Code)

Max Activating Token Index: 496

Text #7

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1427242 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0488. Min Act: -0.0003

Data Index: 1134382 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0477. Min Act: -0.0002

Data Index: 417519 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1607876 (Python Code)

Max Activating Token Index: 218

Text #11

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1629783 (Python Code)

Max Activating Token Index: 649

Text #12

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0471. Min Act: -0.0002

Data Index: 351557 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1402739 (Python Code)

Max Activating Token Index: 923

Text #14

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1440065 (Python Code)

Max Activating Token Index: 464

Text #15

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0476. Min Act: -0.0002

Data Index: 696058 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1564570 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0473. Min Act: -0.0002

Data Index: 102947 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1532129 (Python Code)

Max Activating Token Index: 929

Text #19

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1285409 (C4 (Web Text))

Max Activating Token Index: 682