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

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

Neuron 662 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4301. Min Range: -5.4301

Max Act: 5.4301. Min Act: -0.1700

Data Index: 1340991 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 5.4301. Min Range: -5.4301

Max Act: 5.2738. Min Act: -0.1700

Data Index: 188036 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 5.4301. Min Range: -5.4301

Max Act: 5.2426. Min Act: -0.1700

Data Index: 905621 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 5.4301. Min Range: -5.4301

Max Act: 5.2113. Min Act: -0.1700

Data Index: 631040 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 5.4301. Min Range: -5.4301

Max Act: 5.1176. Min Act: -0.1700

Data Index: 1306751 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 5.4301. Min Range: -5.4301

Max Act: 4.9926. Min Act: -0.1700

Data Index: 66961 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 5.4301. Min Range: -5.4301

Max Act: 5.0238. Min Act: -0.1700

Data Index: 605557 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 5.4301. Min Range: -5.4301

Max Act: 5.0238. Min Act: -0.1700

Data Index: 443172 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 5.4301. Min Range: -5.4301

Max Act: 5.0238. Min Act: -0.1700

Data Index: 235779 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 5.4301. Min Range: -5.4301

Max Act: 4.9926. Min Act: -0.1699

Data Index: 459751 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 5.4301. Min Range: -5.4301

Max Act: 4.9926. Min Act: -0.1700

Data Index: 1036007 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 5.4301. Min Range: -5.4301

Max Act: 4.9613. Min Act: -0.1700

Data Index: 494858 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 5.4301. Min Range: -5.4301

Max Act: 4.9613. Min Act: -0.1700

Data Index: 395997 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 5.4301. Min Range: -5.4301

Max Act: 4.9613. Min Act: -0.1700

Data Index: 1169893 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 5.4301. Min Range: -5.4301

Max Act: 4.8988. Min Act: -0.1700

Data Index: 1042525 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 5.4301. Min Range: -5.4301

Max Act: 4.9301. Min Act: -0.1700

Data Index: 238140 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 5.4301. Min Range: -5.4301

Max Act: 4.9301. Min Act: -0.1700

Data Index: 1114050 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 5.4301. Min Range: -5.4301

Max Act: 4.8988. Min Act: -0.1700

Data Index: 183381 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 5.4301. Min Range: -5.4301

Max Act: 4.8988. Min Act: -0.1700

Data Index: 741436 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 5.4301. Min Range: -5.4301

Max Act: 4.9301. Min Act: -0.1669

Data Index: 192481 (C4 (Web Text))

Max Activating Token Index: 41