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

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

Neuron 1386 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: 4.5437. Min Range: -4.5437

Max Act: 4.5437. Min Act: -0.1700

Data Index: 930955 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 4.5437. Min Range: -4.5437

Max Act: 4.4985. Min Act: -0.1700

Data Index: 391041 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 4.5437. Min Range: -4.5437

Max Act: 4.5169. Min Act: -0.1700

Data Index: 1188069 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 4.5437. Min Range: -4.5437

Max Act: 4.4774. Min Act: -0.1700

Data Index: 1158645 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 4.5437. Min Range: -4.5437

Max Act: 4.4909. Min Act: -0.1700

Data Index: 1354294 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 4.5437. Min Range: -4.5437

Max Act: 4.4899. Min Act: -0.1700

Data Index: 38352 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 4.5437. Min Range: -4.5437

Max Act: 4.4650. Min Act: -0.1700

Data Index: 633322 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 4.5437. Min Range: -4.5437

Max Act: 4.4436. Min Act: -0.1700

Data Index: 36588 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 4.5437. Min Range: -4.5437

Max Act: 4.3854. Min Act: -0.1700

Data Index: 955766 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 4.5437. Min Range: -4.5437

Max Act: 4.3521. Min Act: -0.1700

Data Index: 904526 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 4.5437. Min Range: -4.5437

Max Act: 4.3563. Min Act: -0.1700

Data Index: 337290 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 4.5437. Min Range: -4.5437

Max Act: 4.3310. Min Act: -0.1700

Data Index: 913931 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 4.5437. Min Range: -4.5437

Max Act: 4.3201. Min Act: -0.1700

Data Index: 1198919 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 4.5437. Min Range: -4.5437

Max Act: 4.3201. Min Act: -0.1700

Data Index: 161706 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 4.5437. Min Range: -4.5437

Max Act: 4.3218. Min Act: -0.1700

Data Index: 768862 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 4.5437. Min Range: -4.5437

Max Act: 4.3219. Min Act: -0.1700

Data Index: 119344 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 4.5437. Min Range: -4.5437

Max Act: 4.3228. Min Act: -0.1700

Data Index: 1023376 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 4.5437. Min Range: -4.5437

Max Act: 4.3201. Min Act: -0.1700

Data Index: 271092 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 4.5437. Min Range: -4.5437

Max Act: 4.2785. Min Act: -0.1700

Data Index: 868613 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 4.5437. Min Range: -4.5437

Max Act: 4.2884. Min Act: -0.1700

Data Index: 300138 (C4 (Web Text))

Max Activating Token Index: 341