Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 904 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.7613. Min Act: -0.1638

Data Index: 1376358 (Python Code)

Max Activating Token Index: 418

Text #1

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.4176. Min Act: -0.1699

Data Index: 1532826 (Python Code)

Max Activating Token Index: 144

Text #2

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.4488. Min Act: -0.1699

Data Index: 1624599 (Python Code)

Max Activating Token Index: 826

Text #3

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.3238. Min Act: -0.1692

Data Index: 1599946 (Python Code)

Max Activating Token Index: 399

Text #4

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.2926. Min Act: -0.1700

Data Index: 1649272 (Python Code)

Max Activating Token Index: 454

Text #5

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.2926. Min Act: -0.1700

Data Index: 1228803 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.2613. Min Act: -0.1699

Data Index: 1443493 (Python Code)

Max Activating Token Index: 304

Text #7

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.2301. Min Act: -0.1698

Data Index: 760869 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.2301. Min Act: -0.1696

Data Index: 1645301 (Python Code)

Max Activating Token Index: 531

Text #9

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.2926. Min Act: -0.1699

Data Index: 1065625 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.2613. Min Act: -0.1700

Data Index: 648178 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.2301. Min Act: -0.1700

Data Index: 133093 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.1988. Min Act: -0.1673

Data Index: 984279 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.1363. Min Act: -0.1696

Data Index: 1543523 (Python Code)

Max Activating Token Index: 333

Text #14

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.1676. Min Act: -0.1700

Data Index: 1519654 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.1676. Min Act: -0.1699

Data Index: 916611 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.1676. Min Act: -0.1700

Data Index: 1341820 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.1363. Min Act: -0.1700

Data Index: 1228837 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.1676. Min Act: -0.1699

Data Index: 1467384 (Python Code)

Max Activating Token Index: 415

Text #19

Max Range: 5.7613. Min Range: -5.7613

Max Act: 5.1676. Min Act: -0.1692

Data Index: 186672 (C4 (Web Text))

Max Activating Token Index: 155