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

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

Neuron 426 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: 3.0029. Min Range: -3.0029

Max Act: 3.0029. Min Act: -0.1700

Data Index: 470108 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.0029. Min Range: -3.0029

Max Act: 2.9871. Min Act: -0.1700

Data Index: 268454 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 3.0029. Min Range: -3.0029

Max Act: 2.8762. Min Act: -0.1700

Data Index: 909525 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 3.0029. Min Range: -3.0029

Max Act: 2.8921. Min Act: -0.1700

Data Index: 254953 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 3.0029. Min Range: -3.0029

Max Act: 2.8444. Min Act: -0.1700

Data Index: 1254806 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 3.0029. Min Range: -3.0029

Max Act: 2.8603. Min Act: -0.1700

Data Index: 1177934 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 3.0029. Min Range: -3.0029

Max Act: 2.8444. Min Act: -0.1700

Data Index: 1324293 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 3.0029. Min Range: -3.0029

Max Act: 2.8444. Min Act: -0.1700

Data Index: 1221752 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 3.0029. Min Range: -3.0029

Max Act: 2.8285. Min Act: -0.1700

Data Index: 453809 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 3.0029. Min Range: -3.0029

Max Act: 2.8762. Min Act: -0.1700

Data Index: 925867 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 3.0029. Min Range: -3.0029

Max Act: 2.8444. Min Act: -0.1700

Data Index: 757196 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 3.0029. Min Range: -3.0029

Max Act: 2.8126. Min Act: -0.1700

Data Index: 338348 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 3.0029. Min Range: -3.0029

Max Act: 2.7967. Min Act: -0.1700

Data Index: 746576 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 3.0029. Min Range: -3.0029

Max Act: 2.7967. Min Act: -0.1700

Data Index: 1253290 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 3.0029. Min Range: -3.0029

Max Act: 2.7967. Min Act: -0.1700

Data Index: 976507 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 3.0029. Min Range: -3.0029

Max Act: 2.7648. Min Act: -0.1700

Data Index: 16961 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 3.0029. Min Range: -3.0029

Max Act: 2.7807. Min Act: -0.1700

Data Index: 813127 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 3.0029. Min Range: -3.0029

Max Act: 2.7807. Min Act: -0.1700

Data Index: 1086688 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.0029. Min Range: -3.0029

Max Act: 2.7488. Min Act: -0.1700

Data Index: 882055 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 3.0029. Min Range: -3.0029

Max Act: 2.7648. Min Act: -0.1700

Data Index: 451829 (C4 (Web Text))

Max Activating Token Index: 726