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

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

Neuron 1860 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3306. Min Range: -3.3306

Max Act: 3.3306. Min Act: -0.1699

Data Index: 724211 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 3.3306. Min Range: -3.3306

Max Act: 3.2992. Min Act: -0.1700

Data Index: 717327 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 3.3306. Min Range: -3.3306

Max Act: 3.2835. Min Act: -0.1700

Data Index: 386255 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 3.3306. Min Range: -3.3306

Max Act: 3.2049. Min Act: -0.1700

Data Index: 773691 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 3.3306. Min Range: -3.3306

Max Act: 3.1577. Min Act: -0.1700

Data Index: 628978 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 3.3306. Min Range: -3.3306

Max Act: 3.1262. Min Act: -0.1700

Data Index: 457391 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 3.3306. Min Range: -3.3306

Max Act: 3.0947. Min Act: -0.1700

Data Index: 1060063 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 3.3306. Min Range: -3.3306

Max Act: 3.1104. Min Act: -0.1700

Data Index: 381964 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 3.3306. Min Range: -3.3306

Max Act: 3.1262. Min Act: -0.1700

Data Index: 145995 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 3.3306. Min Range: -3.3306

Max Act: 3.0789. Min Act: -0.1700

Data Index: 230949 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 3.3306. Min Range: -3.3306

Max Act: 3.1104. Min Act: -0.1700

Data Index: 92345 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 3.3306. Min Range: -3.3306

Max Act: 3.0473. Min Act: -0.1700

Data Index: 52794 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 3.3306. Min Range: -3.3306

Max Act: 3.0473. Min Act: -0.1700

Data Index: 859787 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 3.3306. Min Range: -3.3306

Max Act: 2.9999. Min Act: -0.1700

Data Index: 1256789 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 3.3306. Min Range: -3.3306

Max Act: 3.0157. Min Act: -0.1698

Data Index: 156603 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 3.3306. Min Range: -3.3306

Max Act: 3.0631. Min Act: -0.1700

Data Index: 1332844 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 3.3306. Min Range: -3.3306

Max Act: 3.0315. Min Act: -0.1700

Data Index: 911793 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 3.3306. Min Range: -3.3306

Max Act: 2.9999. Min Act: -0.1700

Data Index: 169473 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 3.3306. Min Range: -3.3306

Max Act: 2.9999. Min Act: -0.1700

Data Index: 1052200 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 3.3306. Min Range: -3.3306

Max Act: 2.9683. Min Act: -0.1698

Data Index: 255925 (C4 (Web Text))

Max Activating Token Index: 804