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

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

Neuron 1704 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: 3.7415. Min Range: -3.7415

Max Act: 3.7415. Min Act: -0.1700

Data Index: 627857 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 3.7415. Min Range: -3.7415

Max Act: 3.5366. Min Act: -0.1700

Data Index: 579923 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 3.7415. Min Range: -3.7415

Max Act: 3.5244. Min Act: -0.1700

Data Index: 1232052 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 3.7415. Min Range: -3.7415

Max Act: 3.4981. Min Act: -0.1700

Data Index: 711605 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 3.7415. Min Range: -3.7415

Max Act: 3.4636. Min Act: -0.1700

Data Index: 444587 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 3.7415. Min Range: -3.7415

Max Act: 3.4719. Min Act: -0.1700

Data Index: 932281 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 3.7415. Min Range: -3.7415

Max Act: 3.4660. Min Act: -0.1700

Data Index: 1100959 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 3.7415. Min Range: -3.7415

Max Act: 3.4203. Min Act: -0.1700

Data Index: 344087 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 3.7415. Min Range: -3.7415

Max Act: 3.4418. Min Act: -0.1700

Data Index: 304019 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 3.7415. Min Range: -3.7415

Max Act: 3.4396. Min Act: -0.1700

Data Index: 462142 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 3.7415. Min Range: -3.7415

Max Act: 3.4301. Min Act: -0.1700

Data Index: 11323 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 3.7415. Min Range: -3.7415

Max Act: 3.4390. Min Act: -0.1700

Data Index: 227124 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 3.7415. Min Range: -3.7415

Max Act: 3.4230. Min Act: -0.1700

Data Index: 1164654 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 3.7415. Min Range: -3.7415

Max Act: 3.4128. Min Act: -0.1700

Data Index: 99175 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 3.7415. Min Range: -3.7415

Max Act: 3.4182. Min Act: -0.1700

Data Index: 470332 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 3.7415. Min Range: -3.7415

Max Act: 3.3871. Min Act: -0.1700

Data Index: 562318 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 3.7415. Min Range: -3.7415

Max Act: 3.3838. Min Act: -0.1700

Data Index: 1158202 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 3.7415. Min Range: -3.7415

Max Act: 3.3806. Min Act: -0.1700

Data Index: 661366 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 3.7415. Min Range: -3.7415

Max Act: 3.3969. Min Act: -0.1700

Data Index: 404425 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 3.7415. Min Range: -3.7415

Max Act: 3.3815. Min Act: -0.1700

Data Index: 257682 (C4 (Web Text))

Max Activating Token Index: 824