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

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

Neuron 447 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: 4.0424. Min Range: -4.0424

Max Act: 4.0424. Min Act: -0.1700

Data Index: 420885 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.0424. Min Range: -4.0424

Max Act: 3.9329. Min Act: -0.1700

Data Index: 451045 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 4.0424. Min Range: -4.0424

Max Act: 3.9173. Min Act: -0.1700

Data Index: 941752 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 4.0424. Min Range: -4.0424

Max Act: 3.9486. Min Act: -0.1700

Data Index: 716974 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 4.0424. Min Range: -4.0424

Max Act: 3.8860. Min Act: -0.1700

Data Index: 129586 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 4.0424. Min Range: -4.0424

Max Act: 3.8548. Min Act: -0.1700

Data Index: 234260 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 4.0424. Min Range: -4.0424

Max Act: 3.8391. Min Act: -0.1700

Data Index: 791054 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 4.0424. Min Range: -4.0424

Max Act: 3.8235. Min Act: -0.1700

Data Index: 218936 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 4.0424. Min Range: -4.0424

Max Act: 3.8235. Min Act: -0.1700

Data Index: 1179812 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 4.0424. Min Range: -4.0424

Max Act: 3.8078. Min Act: -0.1700

Data Index: 968195 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 4.0424. Min Range: -4.0424

Max Act: 3.7453. Min Act: -0.1700

Data Index: 526075 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 4.0424. Min Range: -4.0424

Max Act: 3.7922. Min Act: -0.1700

Data Index: 1230599 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 4.0424. Min Range: -4.0424

Max Act: 3.7453. Min Act: -0.1700

Data Index: 894859 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 4.0424. Min Range: -4.0424

Max Act: 3.7453. Min Act: -0.1700

Data Index: 873573 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 4.0424. Min Range: -4.0424

Max Act: 3.7609. Min Act: -0.1700

Data Index: 56725 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.0424. Min Range: -4.0424

Max Act: 3.7453. Min Act: -0.1700

Data Index: 432696 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.0424. Min Range: -4.0424

Max Act: 3.7140. Min Act: -0.1699

Data Index: 334102 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 4.0424. Min Range: -4.0424

Max Act: 3.7453. Min Act: -0.1700

Data Index: 304626 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 4.0424. Min Range: -4.0424

Max Act: 3.6983. Min Act: -0.1700

Data Index: 816047 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 4.0424. Min Range: -4.0424

Max Act: 3.7140. Min Act: -0.1700

Data Index: 748552 (C4 (Web Text))

Max Activating Token Index: 231