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

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

Neuron 616 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.9776. Min Act: -0.1700

Data Index: 301358 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.8585. Min Act: -0.1700

Data Index: 728918 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.8670. Min Act: -0.1700

Data Index: 1630202 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.8499. Min Act: -0.1700

Data Index: 1111263 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.8414. Min Act: -0.1700

Data Index: 402250 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.8499. Min Act: -0.1699

Data Index: 973441 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.8328. Min Act: -0.1700

Data Index: 1649918 (Python Code)

Max Activating Token Index: 2

Text #7

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.8414. Min Act: -0.1700

Data Index: 130912 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.8242. Min Act: -0.1700

Data Index: 63361 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.8242. Min Act: -0.1700

Data Index: 1323189 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.8242. Min Act: -0.1700

Data Index: 280397 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.8071. Min Act: -0.1700

Data Index: 443355 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.8156. Min Act: -0.1700

Data Index: 279064 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.8156. Min Act: -0.1700

Data Index: 1115197 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.7985. Min Act: -0.1700

Data Index: 1269840 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.7985. Min Act: -0.1700

Data Index: 644783 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.7985. Min Act: -0.1700

Data Index: 1019614 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.7985. Min Act: -0.1700

Data Index: 1136732 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.8071. Min Act: -0.1700

Data Index: 807023 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.7985. Min Act: -0.1700

Data Index: 999437 (C4 (Web Text))

Max Activating Token Index: 2