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

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

Neuron 591 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.2181. Min Range: -5.2181

Max Act: 5.2181. Min Act: -0.1700

Data Index: 1208493 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 5.2181. Min Range: -5.2181

Max Act: 5.1243. Min Act: -0.1700

Data Index: 1245651 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 5.2181. Min Range: -5.2181

Max Act: 4.7181. Min Act: -0.1700

Data Index: 784040 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 5.2181. Min Range: -5.2181

Max Act: 4.6243. Min Act: -0.1700

Data Index: 1041431 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 5.2181. Min Range: -5.2181

Max Act: 4.6243. Min Act: -0.1700

Data Index: 1348734 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 5.2181. Min Range: -5.2181

Max Act: 4.5931. Min Act: -0.1700

Data Index: 1191073 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 5.2181. Min Range: -5.2181

Max Act: 4.4681. Min Act: -0.1700

Data Index: 740020 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 5.2181. Min Range: -5.2181

Max Act: 4.4681. Min Act: -0.1700

Data Index: 44074 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 5.2181. Min Range: -5.2181

Max Act: 4.5306. Min Act: -0.1700

Data Index: 226149 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 5.2181. Min Range: -5.2181

Max Act: 4.3431. Min Act: -0.1700

Data Index: 167417 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 5.2181. Min Range: -5.2181

Max Act: 4.3743. Min Act: -0.1700

Data Index: 115482 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 5.2181. Min Range: -5.2181

Max Act: 4.4681. Min Act: -0.1700

Data Index: 602221 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 5.2181. Min Range: -5.2181

Max Act: 4.4681. Min Act: -0.1700

Data Index: 453901 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 5.2181. Min Range: -5.2181

Max Act: 4.4368. Min Act: -0.1700

Data Index: 56837 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 5.2181. Min Range: -5.2181

Max Act: 4.4368. Min Act: -0.1700

Data Index: 1323776 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 5.2181. Min Range: -5.2181

Max Act: 4.4368. Min Act: -0.1700

Data Index: 367892 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 5.2181. Min Range: -5.2181

Max Act: 4.4993. Min Act: -0.1700

Data Index: 699631 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 5.2181. Min Range: -5.2181

Max Act: 4.4056. Min Act: -0.1700

Data Index: 424116 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 5.2181. Min Range: -5.2181

Max Act: 4.4056. Min Act: -0.1700

Data Index: 1039678 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 5.2181. Min Range: -5.2181

Max Act: 4.4681. Min Act: -0.1700

Data Index: 954122 (C4 (Web Text))

Max Activating Token Index: 937