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

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

Neuron 21 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: 3.2843. Min Range: -3.2843

Max Act: 3.2843. Min Act: -0.1699

Data Index: 47602 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 3.2843. Min Range: -3.2843

Max Act: 3.2602. Min Act: -0.1700

Data Index: 1347257 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.2843. Min Range: -3.2843

Max Act: 3.2273. Min Act: -0.1700

Data Index: 265560 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 3.2843. Min Range: -3.2843

Max Act: 3.1933. Min Act: -0.1700

Data Index: 390452 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 3.2843. Min Range: -3.2843

Max Act: 3.1878. Min Act: -0.1700

Data Index: 1165309 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 3.2843. Min Range: -3.2843

Max Act: 3.1616. Min Act: -0.1700

Data Index: 65952 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 3.2843. Min Range: -3.2843

Max Act: 3.1611. Min Act: -0.1700

Data Index: 265372 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 3.2843. Min Range: -3.2843

Max Act: 3.1558. Min Act: -0.1699

Data Index: 748321 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.2843. Min Range: -3.2843

Max Act: 3.1574. Min Act: -0.1699

Data Index: 1254300 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 3.2843. Min Range: -3.2843

Max Act: 3.1451. Min Act: -0.1625

Data Index: 102926 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 3.2843. Min Range: -3.2843

Max Act: 3.1441. Min Act: -0.1699

Data Index: 433320 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 3.2843. Min Range: -3.2843

Max Act: 3.1193. Min Act: -0.1699

Data Index: 914306 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 3.2843. Min Range: -3.2843

Max Act: 3.0906. Min Act: -0.1700

Data Index: 807343 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 3.2843. Min Range: -3.2843

Max Act: 3.1178. Min Act: -0.1420

Data Index: 250186 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 3.2843. Min Range: -3.2843

Max Act: 3.0854. Min Act: -0.1699

Data Index: 919983 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 3.2843. Min Range: -3.2843

Max Act: 3.0904. Min Act: -0.1700

Data Index: 337883 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 3.2843. Min Range: -3.2843

Max Act: 3.1009. Min Act: -0.1700

Data Index: 1290018 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 3.2843. Min Range: -3.2843

Max Act: 3.0764. Min Act: -0.1600

Data Index: 787695 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 3.2843. Min Range: -3.2843

Max Act: 3.0769. Min Act: -0.1699

Data Index: 1176997 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 3.2843. Min Range: -3.2843

Max Act: 3.0688. Min Act: -0.1700

Data Index: 1122138 (C4 (Web Text))

Max Activating Token Index: 658