Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 965 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.6833. Min Act: -0.1700

Data Index: 228026 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.6833. Min Act: -0.1700

Data Index: 1301917 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.5896. Min Act: -0.1700

Data Index: 746108 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.6208. Min Act: -0.1700

Data Index: 521484 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.5896. Min Act: -0.1700

Data Index: 486704 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.3708. Min Act: -0.1700

Data Index: 1030453 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.4646. Min Act: -0.1700

Data Index: 1046720 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.1833. Min Act: -0.1700

Data Index: 445082 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.3083. Min Act: -0.1700

Data Index: 817098 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.1833. Min Act: -0.1700

Data Index: 123372 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.1208. Min Act: -0.1700

Data Index: 1074129 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.2146. Min Act: -0.1700

Data Index: 1188771 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.1521. Min Act: -0.1700

Data Index: 174239 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.1521. Min Act: -0.1700

Data Index: 439713 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.2146. Min Act: -0.1700

Data Index: 998850 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.1208. Min Act: -0.1700

Data Index: 694785 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.0896. Min Act: -0.1700

Data Index: 428380 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.1521. Min Act: -0.1700

Data Index: 291851 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.0896. Min Act: -0.1700

Data Index: 1081167 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.1208. Min Act: -0.1700

Data Index: 1241994 (C4 (Web Text))

Max Activating Token Index: 248