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

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

Neuron 1598 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: 7.7005. Min Range: -7.7005

Max Act: 7.7005. Min Act: -0.1700

Data Index: 377500 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 7.7005. Min Range: -7.7005

Max Act: 7.5755. Min Act: -0.1700

Data Index: 1437555 (Python Code)

Max Activating Token Index: 487

Text #2

Max Range: 7.7005. Min Range: -7.7005

Max Act: 7.5442. Min Act: -0.1700

Data Index: 1411711 (Python Code)

Max Activating Token Index: 953

Text #3

Max Range: 7.7005. Min Range: -7.7005

Max Act: 7.5442. Min Act: -0.1700

Data Index: 1519228 (Python Code)

Max Activating Token Index: 809

Text #4

Max Range: 7.7005. Min Range: -7.7005

Max Act: 7.5442. Min Act: -0.1700

Data Index: 1572507 (Python Code)

Max Activating Token Index: 952

Text #5

Max Range: 7.7005. Min Range: -7.7005

Max Act: 7.4817. Min Act: -0.1700

Data Index: 1558752 (Python Code)

Max Activating Token Index: 956

Text #6

Max Range: 7.7005. Min Range: -7.7005

Max Act: 7.4817. Min Act: -0.1700

Data Index: 1386065 (Python Code)

Max Activating Token Index: 866

Text #7

Max Range: 7.7005. Min Range: -7.7005

Max Act: 7.3880. Min Act: -0.1700

Data Index: 1620094 (Python Code)

Max Activating Token Index: 208

Text #8

Max Range: 7.7005. Min Range: -7.7005

Max Act: 7.3567. Min Act: -0.1700

Data Index: 1562021 (Python Code)

Max Activating Token Index: 935

Text #9

Max Range: 7.7005. Min Range: -7.7005

Max Act: 7.3567. Min Act: -0.1700

Data Index: 1563801 (Python Code)

Max Activating Token Index: 226

Text #10

Max Range: 7.7005. Min Range: -7.7005

Max Act: 7.3880. Min Act: -0.1700

Data Index: 1570444 (Python Code)

Max Activating Token Index: 849

Text #11

Max Range: 7.7005. Min Range: -7.7005

Max Act: 7.3255. Min Act: -0.1700

Data Index: 1374595 (Python Code)

Max Activating Token Index: 1014

Text #12

Max Range: 7.7005. Min Range: -7.7005

Max Act: 7.2942. Min Act: -0.1700

Data Index: 1530526 (Python Code)

Max Activating Token Index: 934

Text #13

Max Range: 7.7005. Min Range: -7.7005

Max Act: 7.2005. Min Act: -0.1700

Data Index: 1627782 (Python Code)

Max Activating Token Index: 886

Text #14

Max Range: 7.7005. Min Range: -7.7005

Max Act: 7.2942. Min Act: -0.1700

Data Index: 1494256 (Python Code)

Max Activating Token Index: 993

Text #15

Max Range: 7.7005. Min Range: -7.7005

Max Act: 7.2630. Min Act: -0.1700

Data Index: 1482394 (Python Code)

Max Activating Token Index: 940

Text #16

Max Range: 7.7005. Min Range: -7.7005

Max Act: 7.1692. Min Act: -0.1700

Data Index: 1274183 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 7.7005. Min Range: -7.7005

Max Act: 7.1692. Min Act: -0.1700

Data Index: 1552708 (Python Code)

Max Activating Token Index: 436

Text #18

Max Range: 7.7005. Min Range: -7.7005

Max Act: 7.0755. Min Act: -0.1700

Data Index: 1600011 (Python Code)

Max Activating Token Index: 480

Text #19

Max Range: 7.7005. Min Range: -7.7005

Max Act: 7.1380. Min Act: -0.1700

Data Index: 1402196 (Python Code)

Max Activating Token Index: 1007