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

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

Neuron 1196 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1329. Min Range: -5.1329

Max Act: 5.1329. Min Act: -0.1700

Data Index: 1103151 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 5.1329. Min Range: -5.1329

Max Act: 5.0079. Min Act: -0.1700

Data Index: 830981 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 5.1329. Min Range: -5.1329

Max Act: 5.0704. Min Act: -0.1700

Data Index: 352734 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 5.1329. Min Range: -5.1329

Max Act: 5.0704. Min Act: -0.1700

Data Index: 1317474 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 5.1329. Min Range: -5.1329

Max Act: 5.0079. Min Act: -0.1700

Data Index: 610591 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 5.1329. Min Range: -5.1329

Max Act: 4.9766. Min Act: -0.1700

Data Index: 552577 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 5.1329. Min Range: -5.1329

Max Act: 4.9454. Min Act: -0.1700

Data Index: 98370 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 5.1329. Min Range: -5.1329

Max Act: 4.9141. Min Act: -0.1700

Data Index: 597646 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 5.1329. Min Range: -5.1329

Max Act: 4.8516. Min Act: -0.1700

Data Index: 156009 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 5.1329. Min Range: -5.1329

Max Act: 4.8829. Min Act: -0.1700

Data Index: 372903 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 5.1329. Min Range: -5.1329

Max Act: 4.8516. Min Act: -0.1700

Data Index: 1120688 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 5.1329. Min Range: -5.1329

Max Act: 4.7891. Min Act: -0.1700

Data Index: 425367 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 5.1329. Min Range: -5.1329

Max Act: 4.7266. Min Act: -0.1700

Data Index: 868870 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 5.1329. Min Range: -5.1329

Max Act: 4.8516. Min Act: -0.1700

Data Index: 1125939 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 5.1329. Min Range: -5.1329

Max Act: 4.8829. Min Act: -0.1700

Data Index: 839152 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 5.1329. Min Range: -5.1329

Max Act: 4.8516. Min Act: -0.1700

Data Index: 154997 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 5.1329. Min Range: -5.1329

Max Act: 4.8516. Min Act: -0.1700

Data Index: 496367 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 5.1329. Min Range: -5.1329

Max Act: 4.8516. Min Act: -0.1700

Data Index: 244695 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 5.1329. Min Range: -5.1329

Max Act: 4.6641. Min Act: -0.1700

Data Index: 579985 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 5.1329. Min Range: -5.1329

Max Act: 4.8204. Min Act: -0.1700

Data Index: 1051458 (C4 (Web Text))

Max Activating Token Index: 121