Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1552 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2316. Min Range: -3.2316

Max Act: 3.2316. Min Act: -0.1700

Data Index: 1065521 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 3.2316. Min Range: -3.2316

Max Act: 3.2316. Min Act: -0.1700

Data Index: 560657 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 3.2316. Min Range: -3.2316

Max Act: 3.1372. Min Act: -0.1700

Data Index: 181002 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 3.2316. Min Range: -3.2316

Max Act: 3.1372. Min Act: -0.1700

Data Index: 849378 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 3.2316. Min Range: -3.2316

Max Act: 3.0741. Min Act: -0.1700

Data Index: 975441 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 3.2316. Min Range: -3.2316

Max Act: 3.0583. Min Act: -0.1700

Data Index: 1541126 (Python Code)

Max Activating Token Index: 964

Text #6

Max Range: 3.2316. Min Range: -3.2316

Max Act: 3.0899. Min Act: -0.1700

Data Index: 1374916 (Python Code)

Max Activating Token Index: 1003

Text #7

Max Range: 3.2316. Min Range: -3.2316

Max Act: 3.1057. Min Act: -0.1700

Data Index: 423334 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 3.2316. Min Range: -3.2316

Max Act: 3.0741. Min Act: -0.1700

Data Index: 821751 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 3.2316. Min Range: -3.2316

Max Act: 3.0741. Min Act: -0.1699

Data Index: 1330733 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 3.2316. Min Range: -3.2316

Max Act: 3.0583. Min Act: -0.1699

Data Index: 1171233 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 3.2316. Min Range: -3.2316

Max Act: 3.0899. Min Act: -0.1700

Data Index: 414550 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 3.2316. Min Range: -3.2316

Max Act: 3.1687. Min Act: -0.1700

Data Index: 1271674 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 3.2316. Min Range: -3.2316

Max Act: 3.0583. Min Act: -0.1700

Data Index: 840246 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 3.2316. Min Range: -3.2316

Max Act: 3.0741. Min Act: -0.1695

Data Index: 1248495 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 3.2316. Min Range: -3.2316

Max Act: 3.0110. Min Act: -0.1700

Data Index: 409610 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 3.2316. Min Range: -3.2316

Max Act: 3.0426. Min Act: -0.1700

Data Index: 636649 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 3.2316. Min Range: -3.2316

Max Act: 3.0426. Min Act: -0.1699

Data Index: 850684 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 3.2316. Min Range: -3.2316

Max Act: 2.9952. Min Act: -0.1700

Data Index: 702823 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 3.2316. Min Range: -3.2316

Max Act: 3.0426. Min Act: -0.1700

Data Index: 1195755 (C4 (Web Text))

Max Activating Token Index: 847