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

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

Neuron 212 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: 7.4970. Min Range: -7.4970

Max Act: 7.4970. Min Act: -0.1700

Data Index: 1071761 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 7.4970. Min Range: -7.4970

Max Act: 7.3720. Min Act: -0.1700

Data Index: 978464 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 7.4970. Min Range: -7.4970

Max Act: 7.4345. Min Act: -0.1700

Data Index: 414288 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 7.4970. Min Range: -7.4970

Max Act: 7.3720. Min Act: -0.1700

Data Index: 621870 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 7.4970. Min Range: -7.4970

Max Act: 7.2470. Min Act: -0.1700

Data Index: 1295829 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 7.4970. Min Range: -7.4970

Max Act: 7.2470. Min Act: -0.1700

Data Index: 877650 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 7.4970. Min Range: -7.4970

Max Act: 7.1845. Min Act: -0.1700

Data Index: 321095 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 7.4970. Min Range: -7.4970

Max Act: 7.2470. Min Act: -0.1700

Data Index: 1251825 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 7.4970. Min Range: -7.4970

Max Act: 7.1220. Min Act: -0.1700

Data Index: 391977 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 7.4970. Min Range: -7.4970

Max Act: 7.1220. Min Act: -0.1700

Data Index: 1292122 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 7.4970. Min Range: -7.4970

Max Act: 7.1845. Min Act: -0.1700

Data Index: 378390 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 7.4970. Min Range: -7.4970

Max Act: 7.2470. Min Act: -0.1700

Data Index: 816504 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 7.4970. Min Range: -7.4970

Max Act: 7.2470. Min Act: -0.1700

Data Index: 29339 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 7.4970. Min Range: -7.4970

Max Act: 7.2470. Min Act: -0.1700

Data Index: 963043 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 7.4970. Min Range: -7.4970

Max Act: 7.1220. Min Act: -0.1700

Data Index: 325219 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 7.4970. Min Range: -7.4970

Max Act: 7.0282. Min Act: -0.1700

Data Index: 1062361 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 7.4970. Min Range: -7.4970

Max Act: 7.1220. Min Act: -0.1700

Data Index: 548185 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 7.4970. Min Range: -7.4970

Max Act: 6.9970. Min Act: -0.1700

Data Index: 221991 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 7.4970. Min Range: -7.4970

Max Act: 7.0595. Min Act: -0.1700

Data Index: 1064504 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 7.4970. Min Range: -7.4970

Max Act: 7.1220. Min Act: -0.1700

Data Index: 1341460 (C4 (Web Text))

Max Activating Token Index: 891