Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 13 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.6288. Min Act: -0.1694

Data Index: 198033 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.6135. Min Act: -0.1480

Data Index: 645896 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.6445. Min Act: -0.1480

Data Index: 136849 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.6336. Min Act: -0.1700

Data Index: 414930 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.5435. Min Act: -0.1695

Data Index: 1041353 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.5092. Min Act: -0.1700

Data Index: 34711 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.5355. Min Act: -0.1480

Data Index: 861493 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.4998. Min Act: -0.1700

Data Index: 1205881 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.4745. Min Act: -0.1697

Data Index: 1361360 (Python Code)

Max Activating Token Index: 192

Text #9

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.4656. Min Act: -0.1700

Data Index: 226509 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.4780. Min Act: -0.1480

Data Index: 543344 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.4861. Min Act: -0.1480

Data Index: 802353 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.4610. Min Act: -0.1697

Data Index: 315047 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.4550. Min Act: -0.1700

Data Index: 866844 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.4596. Min Act: -0.1480

Data Index: 965017 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.4618. Min Act: -0.1681

Data Index: 852478 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.4301. Min Act: -0.1700

Data Index: 1268574 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.4282. Min Act: -0.1700

Data Index: 1300746 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.4216. Min Act: -0.1480

Data Index: 945155 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.4194. Min Act: -0.1689

Data Index: 479718 (C4 (Web Text))

Max Activating Token Index: 275