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

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

Neuron 589 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: 7.9250. Min Range: -7.9250

Max Act: 7.9250. Min Act: -0.1700

Data Index: 1075609 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 7.9250. Min Range: -7.9250

Max Act: 7.7216. Min Act: -0.1698

Data Index: 241657 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 7.9250. Min Range: -7.9250

Max Act: 7.6605. Min Act: -0.1691

Data Index: 1232359 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 7.9250. Min Range: -7.9250

Max Act: 7.6613. Min Act: -0.1699

Data Index: 694225 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 7.9250. Min Range: -7.9250

Max Act: 7.5591. Min Act: -0.1696

Data Index: 746682 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 7.9250. Min Range: -7.9250

Max Act: 7.4672. Min Act: -0.1700

Data Index: 112234 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 7.9250. Min Range: -7.9250

Max Act: 7.4710. Min Act: -0.1695

Data Index: 649187 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 7.9250. Min Range: -7.9250

Max Act: 7.4304. Min Act: -0.1700

Data Index: 739569 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 7.9250. Min Range: -7.9250

Max Act: 7.4381. Min Act: -0.1685

Data Index: 1273769 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 7.9250. Min Range: -7.9250

Max Act: 7.3891. Min Act: -0.1700

Data Index: 375415 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 7.9250. Min Range: -7.9250

Max Act: 7.3769. Min Act: -0.1679

Data Index: 15026 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 7.9250. Min Range: -7.9250

Max Act: 7.3616. Min Act: -0.1700

Data Index: 53404 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 7.9250. Min Range: -7.9250

Max Act: 7.2812. Min Act: -0.1693

Data Index: 1317486 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 7.9250. Min Range: -7.9250

Max Act: 7.2408. Min Act: -0.1699

Data Index: 1239921 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 7.9250. Min Range: -7.9250

Max Act: 7.2529. Min Act: -0.1693

Data Index: 145543 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 7.9250. Min Range: -7.9250

Max Act: 7.1894. Min Act: -0.1692

Data Index: 797805 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 7.9250. Min Range: -7.9250

Max Act: 7.2127. Min Act: -0.1698

Data Index: 608122 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 7.9250. Min Range: -7.9250

Max Act: 7.1651. Min Act: -0.1654

Data Index: 61990 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 7.9250. Min Range: -7.9250

Max Act: 7.1600. Min Act: -0.1698

Data Index: 1030891 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 7.9250. Min Range: -7.9250

Max Act: 7.1705. Min Act: -0.1690

Data Index: 133597 (C4 (Web Text))

Max Activating Token Index: 905