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

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

Neuron 190 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: 5.3783. Min Range: -5.3783

Max Act: 5.3783. Min Act: -0.1700

Data Index: 1048461 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 5.3783. Min Range: -5.3783

Max Act: 5.2533. Min Act: -0.1700

Data Index: 394279 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 5.3783. Min Range: -5.3783

Max Act: 5.1283. Min Act: -0.1700

Data Index: 652557 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 5.3783. Min Range: -5.3783

Max Act: 5.1283. Min Act: -0.1700

Data Index: 674148 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 5.3783. Min Range: -5.3783

Max Act: 5.1595. Min Act: -0.1700

Data Index: 1075468 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 5.3783. Min Range: -5.3783

Max Act: 5.1595. Min Act: -0.1700

Data Index: 908571 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 5.3783. Min Range: -5.3783

Max Act: 5.1283. Min Act: -0.1700

Data Index: 1327994 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 5.3783. Min Range: -5.3783

Max Act: 5.0345. Min Act: -0.1700

Data Index: 222063 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 5.3783. Min Range: -5.3783

Max Act: 5.0345. Min Act: -0.1700

Data Index: 827114 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 5.3783. Min Range: -5.3783

Max Act: 4.9720. Min Act: -0.1700

Data Index: 181891 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 5.3783. Min Range: -5.3783

Max Act: 5.0033. Min Act: -0.1700

Data Index: 1102697 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 5.3783. Min Range: -5.3783

Max Act: 4.9720. Min Act: -0.1700

Data Index: 1142077 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 5.3783. Min Range: -5.3783

Max Act: 4.9720. Min Act: -0.1700

Data Index: 591544 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 5.3783. Min Range: -5.3783

Max Act: 5.0033. Min Act: -0.1700

Data Index: 405452 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 5.3783. Min Range: -5.3783

Max Act: 4.9095. Min Act: -0.1700

Data Index: 1189970 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 5.3783. Min Range: -5.3783

Max Act: 4.8783. Min Act: -0.1700

Data Index: 1302254 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 5.3783. Min Range: -5.3783

Max Act: 4.9095. Min Act: -0.1700

Data Index: 553379 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 5.3783. Min Range: -5.3783

Max Act: 4.8783. Min Act: -0.1700

Data Index: 855904 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 5.3783. Min Range: -5.3783

Max Act: 4.9095. Min Act: -0.1700

Data Index: 390013 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 5.3783. Min Range: -5.3783

Max Act: 4.9408. Min Act: -0.1700

Data Index: 1088574 (C4 (Web Text))

Max Activating Token Index: 91