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

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

Neuron 490 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: 3.7728. Min Range: -3.7728

Max Act: 3.7505. Min Act: -0.0086

Data Index: 168044 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 3.7728. Min Range: -3.7728

Max Act: 3.7728. Min Act: -0.1625

Data Index: 712589 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 3.7728. Min Range: -3.7728

Max Act: 3.6974. Min Act: -0.1698

Data Index: 896512 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 3.7728. Min Range: -3.7728

Max Act: 3.7165. Min Act: -0.1699

Data Index: 228285 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 3.7728. Min Range: -3.7728

Max Act: 3.6776. Min Act: -0.1680

Data Index: 719731 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 3.7728. Min Range: -3.7728

Max Act: 3.6639. Min Act: -0.1689

Data Index: 852552 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 3.7728. Min Range: -3.7728

Max Act: 3.6249. Min Act: 0.0163

Data Index: 1442956 (Python Code)

Max Activating Token Index: 678

Text #7

Max Range: 3.7728. Min Range: -3.7728

Max Act: 3.6196. Min Act: -0.1694

Data Index: 1095262 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 3.7728. Min Range: -3.7728

Max Act: 3.6353. Min Act: -0.1692

Data Index: 1172037 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 3.7728. Min Range: -3.7728

Max Act: 3.5882. Min Act: -0.0906

Data Index: 837080 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 3.7728. Min Range: -3.7728

Max Act: 3.5909. Min Act: -0.1286

Data Index: 1091883 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 3.7728. Min Range: -3.7728

Max Act: 3.5758. Min Act: -0.1699

Data Index: 32916 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 3.7728. Min Range: -3.7728

Max Act: 3.5838. Min Act: -0.1700

Data Index: 250826 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 3.7728. Min Range: -3.7728

Max Act: 3.5674. Min Act: -0.1661

Data Index: 310862 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 3.7728. Min Range: -3.7728

Max Act: 3.5706. Min Act: -0.1509

Data Index: 601417 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 3.7728. Min Range: -3.7728

Max Act: 3.5877. Min Act: -0.1688

Data Index: 1543039 (Python Code)

Max Activating Token Index: 918

Text #16

Max Range: 3.7728. Min Range: -3.7728

Max Act: 3.5411. Min Act: -0.1690

Data Index: 1567926 (Python Code)

Max Activating Token Index: 956

Text #17

Max Range: 3.7728. Min Range: -3.7728

Max Act: 3.5409. Min Act: -0.1692

Data Index: 1484122 (Python Code)

Max Activating Token Index: 546

Text #18

Max Range: 3.7728. Min Range: -3.7728

Max Act: 3.5316. Min Act: -0.1700

Data Index: 929971 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 3.7728. Min Range: -3.7728

Max Act: 3.5540. Min Act: -0.1700

Data Index: 196995 (C4 (Web Text))

Max Activating Token Index: 792