Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1871 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.1323. Min Act: -0.1700

Data Index: 13445 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.8822. Min Act: -0.1700

Data Index: 1527732 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.7414. Min Act: -0.1700

Data Index: 716424 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.7258. Min Act: -0.1700

Data Index: 375922 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.7101. Min Act: -0.1700

Data Index: 540379 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.7570. Min Act: -0.1700

Data Index: 796013 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.7101. Min Act: -0.1700

Data Index: 1284255 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.6945. Min Act: -0.1700

Data Index: 794411 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.6788. Min Act: -0.1700

Data Index: 1299841 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.6319. Min Act: -0.1700

Data Index: 1185875 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.6475. Min Act: -0.1700

Data Index: 1273207 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.6788. Min Act: -0.1700

Data Index: 372708 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.6945. Min Act: -0.1700

Data Index: 732309 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.6788. Min Act: -0.1700

Data Index: 409895 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.6788. Min Act: -0.1700

Data Index: 1120401 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.6475. Min Act: -0.1700

Data Index: 180857 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.6632. Min Act: -0.1700

Data Index: 357394 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.6319. Min Act: -0.1700

Data Index: 837193 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.6475. Min Act: -0.1700

Data Index: 861323 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.6788. Min Act: -0.1700

Data Index: 1072760 (C4 (Web Text))

Max Activating Token Index: 586