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

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

Neuron 349 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: 3.9473. Min Range: -3.9473

Max Act: 3.9473. Min Act: -0.1700

Data Index: 1053751 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.8629. Min Act: -0.1700

Data Index: 236553 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.8141. Min Act: -0.1700

Data Index: 820624 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.7951. Min Act: -0.1700

Data Index: 122238 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.7772. Min Act: -0.1700

Data Index: 483452 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.7925. Min Act: -0.1700

Data Index: 1192797 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.7813. Min Act: -0.1700

Data Index: 708116 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.7480. Min Act: -0.1700

Data Index: 821106 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.7440. Min Act: -0.1700

Data Index: 364917 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.7443. Min Act: -0.1700

Data Index: 1312569 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.7429. Min Act: -0.1700

Data Index: 172710 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.7288. Min Act: -0.1700

Data Index: 1289240 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.7247. Min Act: -0.1700

Data Index: 551365 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.7115. Min Act: -0.1700

Data Index: 1156462 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.7109. Min Act: -0.1700

Data Index: 563252 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.7058. Min Act: -0.1700

Data Index: 545769 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.6881. Min Act: -0.1700

Data Index: 963230 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.6704. Min Act: -0.1700

Data Index: 506155 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.6766. Min Act: -0.1700

Data Index: 410335 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.6530. Min Act: -0.1700

Data Index: 271571 (C4 (Web Text))

Max Activating Token Index: 949