Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 601 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.6399. Min Act: -0.1700

Data Index: 49318 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.4833. Min Act: -0.1700

Data Index: 975418 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.4206. Min Act: -0.1700

Data Index: 169642 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.4519. Min Act: -0.1700

Data Index: 71894 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.4519. Min Act: -0.1700

Data Index: 1008636 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.4206. Min Act: -0.1700

Data Index: 1075163 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.4206. Min Act: -0.1700

Data Index: 450130 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.3264. Min Act: -0.1700

Data Index: 311424 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.3735. Min Act: -0.1700

Data Index: 190301 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.4049. Min Act: -0.1700

Data Index: 6371 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.4676. Min Act: -0.1700

Data Index: 261693 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.4049. Min Act: -0.1700

Data Index: 632355 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.3578. Min Act: -0.1700

Data Index: 1156435 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.3735. Min Act: -0.1700

Data Index: 682809 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.3421. Min Act: -0.1700

Data Index: 673801 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.3735. Min Act: -0.1700

Data Index: 794763 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.3892. Min Act: -0.1700

Data Index: 1211120 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.3578. Min Act: -0.1700

Data Index: 748736 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.3735. Min Act: -0.1700

Data Index: 553808 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.3421. Min Act: -0.1700

Data Index: 25685 (C4 (Web Text))

Max Activating Token Index: 924