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

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

Neuron 121 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: 3.9778. Min Range: -3.9778

Max Act: 3.9778. Min Act: -0.1699

Data Index: 664652 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 3.9778. Min Range: -3.9778

Max Act: 3.9152. Min Act: -0.1700

Data Index: 1321290 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 3.9778. Min Range: -3.9778

Max Act: 3.8839. Min Act: -0.1700

Data Index: 224861 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 3.9778. Min Range: -3.9778

Max Act: 3.8839. Min Act: -0.1700

Data Index: 32248 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 3.9778. Min Range: -3.9778

Max Act: 3.8527. Min Act: -0.1700

Data Index: 1117342 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 3.9778. Min Range: -3.9778

Max Act: 3.8527. Min Act: -0.1700

Data Index: 461205 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 3.9778. Min Range: -3.9778

Max Act: 3.8527. Min Act: -0.1700

Data Index: 1075199 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 3.9778. Min Range: -3.9778

Max Act: 3.8214. Min Act: -0.1700

Data Index: 438836 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 3.9778. Min Range: -3.9778

Max Act: 3.8214. Min Act: -0.1700

Data Index: 462592 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 3.9778. Min Range: -3.9778

Max Act: 3.7901. Min Act: -0.1700

Data Index: 38949 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 3.9778. Min Range: -3.9778

Max Act: 3.7901. Min Act: -0.1700

Data Index: 11819 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 3.9778. Min Range: -3.9778

Max Act: 3.7901. Min Act: -0.1700

Data Index: 969081 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 3.9778. Min Range: -3.9778

Max Act: 3.8214. Min Act: -0.1700

Data Index: 878845 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 3.9778. Min Range: -3.9778

Max Act: 3.7901. Min Act: -0.1700

Data Index: 69502 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 3.9778. Min Range: -3.9778

Max Act: 3.7432. Min Act: -0.1700

Data Index: 1057816 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 3.9778. Min Range: -3.9778

Max Act: 3.7119. Min Act: -0.1700

Data Index: 71724 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 3.9778. Min Range: -3.9778

Max Act: 3.7119. Min Act: -0.1700

Data Index: 45055 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 3.9778. Min Range: -3.9778

Max Act: 3.6336. Min Act: -0.1700

Data Index: 868200 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 3.9778. Min Range: -3.9778

Max Act: 3.6962. Min Act: -0.1700

Data Index: 203566 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 3.9778. Min Range: -3.9778

Max Act: 3.7119. Min Act: -0.1699

Data Index: 349219 (C4 (Web Text))

Max Activating Token Index: 710