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

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

Neuron 221 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: 3.8744. Min Range: -3.8744

Max Act: 3.8744. Min Act: -0.1697

Data Index: 1160987 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 3.8744. Min Range: -3.8744

Max Act: 3.8334. Min Act: -0.1641

Data Index: 729933 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 3.8744. Min Range: -3.8744

Max Act: 3.7835. Min Act: -0.1698

Data Index: 565047 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 3.8744. Min Range: -3.8744

Max Act: 3.7455. Min Act: -0.1699

Data Index: 7626 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 3.8744. Min Range: -3.8744

Max Act: 3.6915. Min Act: -0.1641

Data Index: 437558 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 3.8744. Min Range: -3.8744

Max Act: 3.7138. Min Act: -0.1700

Data Index: 138463 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 3.8744. Min Range: -3.8744

Max Act: 3.6870. Min Act: -0.1641

Data Index: 973822 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 3.8744. Min Range: -3.8744

Max Act: 3.6920. Min Act: -0.1700

Data Index: 1001793 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 3.8744. Min Range: -3.8744

Max Act: 3.6669. Min Act: -0.1641

Data Index: 521382 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 3.8744. Min Range: -3.8744

Max Act: 3.6786. Min Act: -0.1662

Data Index: 1316732 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 3.8744. Min Range: -3.8744

Max Act: 3.6783. Min Act: -0.1700

Data Index: 585814 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 3.8744. Min Range: -3.8744

Max Act: 3.6754. Min Act: -0.1700

Data Index: 971055 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 3.8744. Min Range: -3.8744

Max Act: 3.6315. Min Act: -0.1641

Data Index: 1127262 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 3.8744. Min Range: -3.8744

Max Act: 3.6293. Min Act: -0.1700

Data Index: 1134353 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 3.8744. Min Range: -3.8744

Max Act: 3.6417. Min Act: -0.1697

Data Index: 381438 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 3.8744. Min Range: -3.8744

Max Act: 3.6394. Min Act: -0.1641

Data Index: 1074109 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 3.8744. Min Range: -3.8744

Max Act: 3.6279. Min Act: -0.1671

Data Index: 159243 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 3.8744. Min Range: -3.8744

Max Act: 3.6490. Min Act: -0.1700

Data Index: 361479 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 3.8744. Min Range: -3.8744

Max Act: 3.6523. Min Act: -0.1698

Data Index: 372693 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 3.8744. Min Range: -3.8744

Max Act: 3.6568. Min Act: -0.1699

Data Index: 459873 (C4 (Web Text))

Max Activating Token Index: 513