Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1199 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.3411. Min Act: -0.1699

Data Index: 503386 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.2241. Min Act: -0.1700

Data Index: 844283 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.2007. Min Act: -0.1700

Data Index: 1614237 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.2145. Min Act: -0.1700

Data Index: 1001000 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.2493. Min Act: -0.1700

Data Index: 47039 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.1685. Min Act: -0.1698

Data Index: 1396872 (Python Code)

Max Activating Token Index: 284

Text #6

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.1723. Min Act: -0.1700

Data Index: 1448610 (Python Code)

Max Activating Token Index: 309

Text #7

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.1727. Min Act: -0.1699

Data Index: 1655813 (Python Code)

Max Activating Token Index: 991

Text #8

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.1302. Min Act: -0.1700

Data Index: 1433146 (Python Code)

Max Activating Token Index: 992

Text #9

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.0949. Min Act: -0.1700

Data Index: 57812 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.1141. Min Act: -0.1700

Data Index: 1523193 (Python Code)

Max Activating Token Index: 481

Text #11

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.0780. Min Act: -0.1700

Data Index: 1471750 (Python Code)

Max Activating Token Index: 818

Text #12

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.0580. Min Act: -0.1696

Data Index: 1560561 (Python Code)

Max Activating Token Index: 890

Text #13

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.0690. Min Act: -0.1700

Data Index: 1483893 (Python Code)

Max Activating Token Index: 975

Text #14

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.0460. Min Act: -0.1700

Data Index: 1473476 (Python Code)

Max Activating Token Index: 478

Text #15

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.0838. Min Act: -0.1700

Data Index: 1595561 (Python Code)

Max Activating Token Index: 479

Text #16

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.0480. Min Act: -0.1699

Data Index: 1476022 (Python Code)

Max Activating Token Index: 750

Text #17

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.0282. Min Act: -0.1700

Data Index: 27253 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.0396. Min Act: -0.1700

Data Index: 1654196 (Python Code)

Max Activating Token Index: 997

Text #19

Max Range: 4.3411. Min Range: -4.3411

Max Act: 4.0355. Min Act: -0.1700

Data Index: 1586602 (Python Code)

Max Activating Token Index: 323