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

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

Neuron 3962 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0770. Min Act: -0.0000

Data Index: 1052294 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0756. Min Act: -0.0000

Data Index: 1117831 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0691. Min Act: -0.0000

Data Index: 674457 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0662. Min Act: -0.0000

Data Index: 295028 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0669. Min Act: -0.0000

Data Index: 299544 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0547. Min Act: -0.0000

Data Index: 531558 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0559. Min Act: -0.0000

Data Index: 263233 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0625. Min Act: -0.0000

Data Index: 1200338 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0619. Min Act: -0.0000

Data Index: 1534417 (Python Code)

Max Activating Token Index: 210

Text #9

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1366299 (Python Code)

Max Activating Token Index: 835

Text #10

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0597. Min Act: -0.0000

Data Index: 938071 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0601. Min Act: -0.0000

Data Index: 1560849 (Python Code)

Max Activating Token Index: 805

Text #12

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0546. Min Act: -0.0000

Data Index: 453654 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0574. Min Act: -0.0000

Data Index: 1632066 (Python Code)

Max Activating Token Index: 340

Text #14

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0549. Min Act: -0.0000

Data Index: 619228 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0560. Min Act: -0.0000

Data Index: 417537 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0497. Min Act: -0.0000

Data Index: 1156153 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0441. Min Act: -0.0000

Data Index: 1369220 (Python Code)

Max Activating Token Index: 338

Text #18

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0533. Min Act: -0.0000

Data Index: 1348100 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0469. Min Act: -0.0000

Data Index: 1515405 (Python Code)

Max Activating Token Index: 466