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

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

Neuron 707 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: 5.4425. Min Range: -5.4425

Max Act: 5.4425. Min Act: -0.1700

Data Index: 634152 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 5.4425. Min Range: -5.4425

Max Act: 5.3175. Min Act: -0.1700

Data Index: 523197 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 5.4425. Min Range: -5.4425

Max Act: 5.2550. Min Act: -0.1700

Data Index: 263989 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 5.4425. Min Range: -5.4425

Max Act: 5.2863. Min Act: -0.1700

Data Index: 1211443 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 5.4425. Min Range: -5.4425

Max Act: 5.1925. Min Act: -0.1700

Data Index: 916536 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 5.4425. Min Range: -5.4425

Max Act: 5.1613. Min Act: -0.1700

Data Index: 947486 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 5.4425. Min Range: -5.4425

Max Act: 5.1925. Min Act: -0.1700

Data Index: 626081 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 5.4425. Min Range: -5.4425

Max Act: 5.1925. Min Act: -0.1700

Data Index: 854692 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 5.4425. Min Range: -5.4425

Max Act: 5.0988. Min Act: -0.1700

Data Index: 789072 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 5.4425. Min Range: -5.4425

Max Act: 5.1925. Min Act: -0.1700

Data Index: 543856 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 5.4425. Min Range: -5.4425

Max Act: 5.2238. Min Act: -0.1700

Data Index: 563036 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 5.4425. Min Range: -5.4425

Max Act: 5.1925. Min Act: -0.1700

Data Index: 1259697 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 5.4425. Min Range: -5.4425

Max Act: 5.1300. Min Act: -0.1700

Data Index: 1115405 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 5.4425. Min Range: -5.4425

Max Act: 5.1300. Min Act: -0.1700

Data Index: 61191 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 5.4425. Min Range: -5.4425

Max Act: 5.1300. Min Act: -0.1700

Data Index: 86585 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 5.4425. Min Range: -5.4425

Max Act: 5.1300. Min Act: -0.1700

Data Index: 1279085 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 5.4425. Min Range: -5.4425

Max Act: 5.0988. Min Act: -0.1700

Data Index: 639941 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 5.4425. Min Range: -5.4425

Max Act: 5.0988. Min Act: -0.1700

Data Index: 536843 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 5.4425. Min Range: -5.4425

Max Act: 5.0988. Min Act: -0.1700

Data Index: 292312 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 5.4425. Min Range: -5.4425

Max Act: 5.0675. Min Act: -0.1700

Data Index: 960083 (C4 (Web Text))

Max Activating Token Index: 865