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

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

Neuron 202 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: 3.7986. Min Range: -3.7986

Max Act: 3.7986. Min Act: -0.1700

Data Index: 1320195 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 3.7986. Min Range: -3.7986

Max Act: 3.7986. Min Act: -0.1700

Data Index: 149008 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 3.7986. Min Range: -3.7986

Max Act: 3.7673. Min Act: -0.1700

Data Index: 492039 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 3.7986. Min Range: -3.7986

Max Act: 3.5952. Min Act: -0.1700

Data Index: 445912 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 3.7986. Min Range: -3.7986

Max Act: 3.6109. Min Act: -0.1700

Data Index: 1211660 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 3.7986. Min Range: -3.7986

Max Act: 3.5169. Min Act: -0.1700

Data Index: 989710 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 3.7986. Min Range: -3.7986

Max Act: 3.5169. Min Act: -0.1700

Data Index: 51269 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 3.7986. Min Range: -3.7986

Max Act: 3.5482. Min Act: -0.1700

Data Index: 292399 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 3.7986. Min Range: -3.7986

Max Act: 3.5012. Min Act: -0.1700

Data Index: 124585 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 3.7986. Min Range: -3.7986

Max Act: 3.5326. Min Act: -0.1700

Data Index: 851608 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 3.7986. Min Range: -3.7986

Max Act: 3.5169. Min Act: -0.1699

Data Index: 1504586 (Python Code)

Max Activating Token Index: 905

Text #11

Max Range: 3.7986. Min Range: -3.7986

Max Act: 3.5012. Min Act: -0.1700

Data Index: 1142222 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 3.7986. Min Range: -3.7986

Max Act: 3.5326. Min Act: -0.1700

Data Index: 622284 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 3.7986. Min Range: -3.7986

Max Act: 3.4855. Min Act: -0.1700

Data Index: 385719 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 3.7986. Min Range: -3.7986

Max Act: 3.4699. Min Act: -0.1700

Data Index: 1155299 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 3.7986. Min Range: -3.7986

Max Act: 3.4855. Min Act: -0.1700

Data Index: 895115 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 3.7986. Min Range: -3.7986

Max Act: 3.5012. Min Act: -0.1700

Data Index: 1180892 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 3.7986. Min Range: -3.7986

Max Act: 3.4542. Min Act: -0.1699

Data Index: 1253504 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.7986. Min Range: -3.7986

Max Act: 3.4542. Min Act: -0.1700

Data Index: 714267 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 3.7986. Min Range: -3.7986

Max Act: 3.4072. Min Act: -0.1699

Data Index: 1552407 (Python Code)

Max Activating Token Index: 767