Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3591 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2384. Min Act: -0.0001

Data Index: 58823 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2074. Min Act: -0.0000

Data Index: 270430 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1980. Min Act: -0.0001

Data Index: 1621533 (Python Code)

Max Activating Token Index: 298

Text #3

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1916. Min Act: -0.0001

Data Index: 466845 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1981. Min Act: -0.0001

Data Index: 1517601 (Python Code)

Max Activating Token Index: 298

Text #5

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1884. Min Act: -0.0001

Data Index: 1582797 (Python Code)

Max Activating Token Index: 509

Text #6

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1599219 (Python Code)

Max Activating Token Index: 464

Text #7

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1777. Min Act: -0.0001

Data Index: 265158 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1652. Min Act: -0.0001

Data Index: 1492950 (Python Code)

Max Activating Token Index: 938

Text #9

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1692. Min Act: -0.0000

Data Index: 1196452 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1467. Min Act: -0.0001

Data Index: 1268439 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1654019 (Python Code)

Max Activating Token Index: 471

Text #12

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1622. Min Act: -0.0000

Data Index: 1076288 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1680. Min Act: -0.0001

Data Index: 1407827 (Python Code)

Max Activating Token Index: 907

Text #14

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1554. Min Act: -0.0001

Data Index: 1585163 (Python Code)

Max Activating Token Index: 551

Text #15

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1592. Min Act: -0.0000

Data Index: 235794 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1595. Min Act: -0.0000

Data Index: 686340 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1585. Min Act: -0.0001

Data Index: 1631491 (Python Code)

Max Activating Token Index: 413

Text #18

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1591731 (Python Code)

Max Activating Token Index: 191

Text #19

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1629. Min Act: -0.0001

Data Index: 1620270 (Python Code)

Max Activating Token Index: 854