Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1433 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.0825. Min Range: -5.0825

Max Act: 5.0825. Min Act: -0.1700

Data Index: 1251953 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 5.0825. Min Range: -5.0825

Max Act: 5.0200. Min Act: -0.1700

Data Index: 1298891 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 5.0825. Min Range: -5.0825

Max Act: 5.0200. Min Act: -0.1700

Data Index: 820244 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.9575. Min Act: -0.1700

Data Index: 332549 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.9888. Min Act: -0.1700

Data Index: 266938 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.8950. Min Act: -0.1700

Data Index: 1070671 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.8950. Min Act: -0.1700

Data Index: 1053399 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.8950. Min Act: -0.1700

Data Index: 597276 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.8325. Min Act: -0.1700

Data Index: 701769 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.8013. Min Act: -0.1700

Data Index: 594776 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.8325. Min Act: -0.1700

Data Index: 148746 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.7700. Min Act: -0.1700

Data Index: 1279554 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.8325. Min Act: -0.1700

Data Index: 1042725 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.8013. Min Act: -0.1700

Data Index: 482277 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.7388. Min Act: -0.1700

Data Index: 72967 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.7700. Min Act: -0.1700

Data Index: 1329603 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.7388. Min Act: -0.1700

Data Index: 1054233 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.8013. Min Act: -0.1700

Data Index: 277189 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.7700. Min Act: -0.1700

Data Index: 240716 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 5.0825. Min Range: -5.0825

Max Act: 4.7075. Min Act: -0.1700

Data Index: 1277942 (C4 (Web Text))

Max Activating Token Index: 951