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

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

Neuron 196 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: 5.3082. Min Range: -5.3082

Max Act: 5.3082. Min Act: -0.1700

Data Index: 1167281 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 5.3082. Min Range: -5.3082

Max Act: 5.1832. Min Act: -0.1700

Data Index: 1249115 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 5.3082. Min Range: -5.3082

Max Act: 5.2769. Min Act: -0.1699

Data Index: 1065666 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 5.3082. Min Range: -5.3082

Max Act: 5.2457. Min Act: -0.1700

Data Index: 218567 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 5.3082. Min Range: -5.3082

Max Act: 5.2144. Min Act: -0.1698

Data Index: 185009 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 5.3082. Min Range: -5.3082

Max Act: 5.2144. Min Act: -0.1699

Data Index: 1292805 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 5.3082. Min Range: -5.3082

Max Act: 5.1832. Min Act: -0.1697

Data Index: 1158222 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 5.3082. Min Range: -5.3082

Max Act: 5.1519. Min Act: -0.1700

Data Index: 1295127 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 5.3082. Min Range: -5.3082

Max Act: 5.1207. Min Act: -0.1700

Data Index: 238949 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 5.3082. Min Range: -5.3082

Max Act: 5.1207. Min Act: -0.1700

Data Index: 593476 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 5.3082. Min Range: -5.3082

Max Act: 5.0582. Min Act: -0.1700

Data Index: 724353 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 5.3082. Min Range: -5.3082

Max Act: 5.0582. Min Act: -0.1700

Data Index: 1309146 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 5.3082. Min Range: -5.3082

Max Act: 5.0269. Min Act: -0.1695

Data Index: 325529 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 5.3082. Min Range: -5.3082

Max Act: 5.0582. Min Act: -0.1700

Data Index: 557373 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 5.3082. Min Range: -5.3082

Max Act: 4.9644. Min Act: -0.1700

Data Index: 411113 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 5.3082. Min Range: -5.3082

Max Act: 5.0582. Min Act: -0.1700

Data Index: 179253 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 5.3082. Min Range: -5.3082

Max Act: 5.0269. Min Act: -0.1700

Data Index: 241041 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 5.3082. Min Range: -5.3082

Max Act: 5.0582. Min Act: -0.1700

Data Index: 903565 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 5.3082. Min Range: -5.3082

Max Act: 4.9644. Min Act: -0.1700

Data Index: 251001 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 5.3082. Min Range: -5.3082

Max Act: 4.9957. Min Act: -0.1700

Data Index: 1107904 (C4 (Web Text))

Max Activating Token Index: 274