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

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

Neuron 100 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: 3.4679. Min Range: -3.4679

Max Act: 3.4679. Min Act: -0.1700

Data Index: 1287993 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 3.4679. Min Range: -3.4679

Max Act: 3.4231. Min Act: -0.1700

Data Index: 1034760 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 3.4679. Min Range: -3.4679

Max Act: 3.4063. Min Act: -0.1700

Data Index: 683776 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 3.4679. Min Range: -3.4679

Max Act: 3.4114. Min Act: -0.1700

Data Index: 147176 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 3.4679. Min Range: -3.4679

Max Act: 3.3582. Min Act: -0.1700

Data Index: 378672 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 3.4679. Min Range: -3.4679

Max Act: 3.3344. Min Act: -0.1700

Data Index: 601763 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 3.4679. Min Range: -3.4679

Max Act: 3.3600. Min Act: -0.1700

Data Index: 108326 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 3.4679. Min Range: -3.4679

Max Act: 3.3436. Min Act: -0.1700

Data Index: 1254601 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 3.4679. Min Range: -3.4679

Max Act: 3.3184. Min Act: -0.1700

Data Index: 586697 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 3.4679. Min Range: -3.4679

Max Act: 3.3100. Min Act: -0.1700

Data Index: 1084349 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 3.4679. Min Range: -3.4679

Max Act: 3.3074. Min Act: -0.1700

Data Index: 1339320 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 3.4679. Min Range: -3.4679

Max Act: 3.2363. Min Act: -0.1700

Data Index: 571312 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 3.4679. Min Range: -3.4679

Max Act: 3.2258. Min Act: -0.1700

Data Index: 553723 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 3.4679. Min Range: -3.4679

Max Act: 3.2276. Min Act: -0.1700

Data Index: 424259 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 3.4679. Min Range: -3.4679

Max Act: 3.2412. Min Act: -0.1700

Data Index: 45534 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 3.4679. Min Range: -3.4679

Max Act: 3.2453. Min Act: -0.1700

Data Index: 461409 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 3.4679. Min Range: -3.4679

Max Act: 3.2217. Min Act: -0.1700

Data Index: 844905 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 3.4679. Min Range: -3.4679

Max Act: 3.2297. Min Act: -0.1700

Data Index: 1580415 (Python Code)

Max Activating Token Index: 9

Text #18

Max Range: 3.4679. Min Range: -3.4679

Max Act: 3.2228. Min Act: -0.1700

Data Index: 735121 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 3.4679. Min Range: -3.4679

Max Act: 3.2057. Min Act: -0.1700

Data Index: 431066 (C4 (Web Text))

Max Activating Token Index: 546