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

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

Neuron 162 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.2412. Min Act: -0.1700

Data Index: 1003959 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.2255. Min Act: -0.1700

Data Index: 1277279 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.2255. Min Act: -0.1700

Data Index: 1142665 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.2412. Min Act: -0.1700

Data Index: 687731 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.2412. Min Act: -0.1700

Data Index: 277004 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.1626. Min Act: -0.1700

Data Index: 78922 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.1783. Min Act: -0.1700

Data Index: 775847 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.1783. Min Act: -0.1700

Data Index: 682222 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.1626. Min Act: -0.1700

Data Index: 1317490 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.1783. Min Act: -0.1700

Data Index: 643648 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.1468. Min Act: -0.1700

Data Index: 884213 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.1626. Min Act: -0.1700

Data Index: 1225629 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.1468. Min Act: -0.1700

Data Index: 775126 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.1468. Min Act: -0.1700

Data Index: 833115 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.1311. Min Act: -0.1700

Data Index: 1073205 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.1311. Min Act: -0.1700

Data Index: 754305 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.0995. Min Act: -0.1700

Data Index: 44400 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.1153. Min Act: -0.1700

Data Index: 279052 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.1311. Min Act: -0.1700

Data Index: 299577 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 3.2412. Min Range: -3.2412

Max Act: 3.1153. Min Act: -0.1700

Data Index: 819519 (C4 (Web Text))

Max Activating Token Index: 693