Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 471 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.6779. Min Act: -0.1700

Data Index: 1064709 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.5840. Min Act: -0.1700

Data Index: 741264 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.5527. Min Act: -0.1700

Data Index: 711047 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.6153. Min Act: -0.1700

Data Index: 108819 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.5213. Min Act: -0.1700

Data Index: 154481 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.5213. Min Act: -0.1700

Data Index: 611179 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.5213. Min Act: -0.1700

Data Index: 443344 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.5213. Min Act: -0.1700

Data Index: 505459 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.5213. Min Act: -0.1700

Data Index: 348238 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.4587. Min Act: -0.1700

Data Index: 12159 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.4900. Min Act: -0.1700

Data Index: 204440 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.4587. Min Act: -0.1700

Data Index: 1202660 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.4900. Min Act: -0.1700

Data Index: 915152 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.4900. Min Act: -0.1700

Data Index: 262373 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.4587. Min Act: -0.1700

Data Index: 516171 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.4587. Min Act: -0.1700

Data Index: 25216 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.4587. Min Act: -0.1700

Data Index: 74768 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.4273. Min Act: -0.1700

Data Index: 870663 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.4116. Min Act: -0.1700

Data Index: 466708 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.4116. Min Act: -0.1700

Data Index: 388977 (C4 (Web Text))

Max Activating Token Index: 1019