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

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

Neuron 1345 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: 5.4444. Min Range: -5.4444

Max Act: 5.4444. Min Act: -0.1699

Data Index: 992035 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 5.4444. Min Range: -5.4444

Max Act: 5.2995. Min Act: -0.1689

Data Index: 44023 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 5.4444. Min Range: -5.4444

Max Act: 5.2738. Min Act: -0.0121

Data Index: 1503122 (Python Code)

Max Activating Token Index: 634

Text #3

Max Range: 5.4444. Min Range: -5.4444

Max Act: 5.2942. Min Act: -0.1690

Data Index: 1010776 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 5.4444. Min Range: -5.4444

Max Act: 5.2107. Min Act: -0.1700

Data Index: 1239585 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 5.4444. Min Range: -5.4444

Max Act: 5.1567. Min Act: -0.1697

Data Index: 947118 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 5.4444. Min Range: -5.4444

Max Act: 5.1251. Min Act: -0.1666

Data Index: 1262507 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 5.4444. Min Range: -5.4444

Max Act: 5.1333. Min Act: -0.1697

Data Index: 859535 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 5.4444. Min Range: -5.4444

Max Act: 5.1389. Min Act: -0.1700

Data Index: 801459 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 5.4444. Min Range: -5.4444

Max Act: 5.0786. Min Act: -0.1698

Data Index: 567316 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 5.4444. Min Range: -5.4444

Max Act: 5.0475. Min Act: -0.1699

Data Index: 1205901 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 5.4444. Min Range: -5.4444

Max Act: 5.0769. Min Act: -0.1699

Data Index: 1006429 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 5.4444. Min Range: -5.4444

Max Act: 5.0224. Min Act: -0.1699

Data Index: 1234684 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 5.4444. Min Range: -5.4444

Max Act: 5.0153. Min Act: -0.1695

Data Index: 1324093 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 5.4444. Min Range: -5.4444

Max Act: 5.0272. Min Act: -0.1698

Data Index: 218345 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 5.4444. Min Range: -5.4444

Max Act: 4.9912. Min Act: -0.1696

Data Index: 447453 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 5.4444. Min Range: -5.4444

Max Act: 4.9575. Min Act: -0.1700

Data Index: 400719 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 5.4444. Min Range: -5.4444

Max Act: 4.9848. Min Act: -0.1699

Data Index: 777781 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 5.4444. Min Range: -5.4444

Max Act: 4.9535. Min Act: -0.1700

Data Index: 317178 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 5.4444. Min Range: -5.4444

Max Act: 4.9151. Min Act: -0.0121

Data Index: 1538878 (Python Code)

Max Activating Token Index: 542