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

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

Neuron 1934 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: 4.0989. Min Range: -4.0989

Max Act: 4.0989. Min Act: -0.1696

Data Index: 1583506 (Python Code)

Max Activating Token Index: 731

Text #1

Max Range: 4.0989. Min Range: -4.0989

Max Act: 4.0364. Min Act: -0.1698

Data Index: 1378356 (Python Code)

Max Activating Token Index: 445

Text #2

Max Range: 4.0989. Min Range: -4.0989

Max Act: 3.9426. Min Act: -0.1699

Data Index: 1511432 (Python Code)

Max Activating Token Index: 252

Text #3

Max Range: 4.0989. Min Range: -4.0989

Max Act: 3.8175. Min Act: -0.1700

Data Index: 1646378 (Python Code)

Max Activating Token Index: 93

Text #4

Max Range: 4.0989. Min Range: -4.0989

Max Act: 3.8175. Min Act: -0.1699

Data Index: 1397743 (Python Code)

Max Activating Token Index: 723

Text #5

Max Range: 4.0989. Min Range: -4.0989

Max Act: 3.8175. Min Act: -0.1699

Data Index: 1597444 (Python Code)

Max Activating Token Index: 460

Text #6

Max Range: 4.0989. Min Range: -4.0989

Max Act: 3.6611. Min Act: -0.1700

Data Index: 917051 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 4.0989. Min Range: -4.0989

Max Act: 3.6298. Min Act: -0.1700

Data Index: 1639818 (Python Code)

Max Activating Token Index: 696

Text #8

Max Range: 4.0989. Min Range: -4.0989

Max Act: 3.6924. Min Act: -0.1700

Data Index: 145284 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 4.0989. Min Range: -4.0989

Max Act: 3.6611. Min Act: -0.1700

Data Index: 1576601 (Python Code)

Max Activating Token Index: 978

Text #10

Max Range: 4.0989. Min Range: -4.0989

Max Act: 3.5985. Min Act: -0.1700

Data Index: 1476357 (Python Code)

Max Activating Token Index: 923

Text #11

Max Range: 4.0989. Min Range: -4.0989

Max Act: 3.5671. Min Act: -0.1700

Data Index: 1578246 (Python Code)

Max Activating Token Index: 1018

Text #12

Max Range: 4.0989. Min Range: -4.0989

Max Act: 3.5671. Min Act: -0.1700

Data Index: 154612 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 4.0989. Min Range: -4.0989

Max Act: 3.5358. Min Act: -0.1700

Data Index: 1405859 (Python Code)

Max Activating Token Index: 726

Text #14

Max Range: 4.0989. Min Range: -4.0989

Max Act: 3.5358. Min Act: -0.1700

Data Index: 1598700 (Python Code)

Max Activating Token Index: 528

Text #15

Max Range: 4.0989. Min Range: -4.0989

Max Act: 3.5358. Min Act: -0.1700

Data Index: 1529963 (Python Code)

Max Activating Token Index: 934

Text #16

Max Range: 4.0989. Min Range: -4.0989

Max Act: 3.5045. Min Act: -0.1699

Data Index: 1529189 (Python Code)

Max Activating Token Index: 369

Text #17

Max Range: 4.0989. Min Range: -4.0989

Max Act: 3.5045. Min Act: -0.1700

Data Index: 1577894 (Python Code)

Max Activating Token Index: 1003

Text #18

Max Range: 4.0989. Min Range: -4.0989

Max Act: 3.5358. Min Act: -0.1699

Data Index: 1523584 (Python Code)

Max Activating Token Index: 1011

Text #19

Max Range: 4.0989. Min Range: -4.0989

Max Act: 3.5045. Min Act: -0.1700

Data Index: 1513620 (Python Code)

Max Activating Token Index: 568