Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 177 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.9736. Min Act: -0.1700

Data Index: 959544 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.7080. Min Act: -0.1700

Data Index: 263878 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.6299. Min Act: -0.1700

Data Index: 803593 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.5830. Min Act: -0.1700

Data Index: 1091940 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.5049. Min Act: -0.1700

Data Index: 61947 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.4580. Min Act: -0.1700

Data Index: 743602 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.4892. Min Act: -0.1700

Data Index: 221309 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.4580. Min Act: -0.1700

Data Index: 332036 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.4580. Min Act: -0.1700

Data Index: 813093 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.3486. Min Act: -0.1700

Data Index: 1163469 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.2861. Min Act: -0.1700

Data Index: 467750 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.2392. Min Act: -0.1700

Data Index: 1316704 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.3330. Min Act: -0.1700

Data Index: 571252 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.2392. Min Act: -0.1700

Data Index: 714190 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.2236. Min Act: -0.1700

Data Index: 183818 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.2549. Min Act: -0.1700

Data Index: 1532962 (Python Code)

Max Activating Token Index: 230

Text #16

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.1455. Min Act: -0.1700

Data Index: 305910 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.1299. Min Act: -0.1700

Data Index: 1157751 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.0986. Min Act: -0.1700

Data Index: 620 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 7.9736. Min Range: -7.9736

Max Act: 7.0830. Min Act: -0.1700

Data Index: 1603241 (Python Code)

Max Activating Token Index: 798