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

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

Neuron 258 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.2380. Min Act: -0.1700

Data Index: 1178670 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.1908. Min Act: -0.1700

Data Index: 1258641 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.1750. Min Act: -0.1700

Data Index: 293133 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.1750. Min Act: -0.1700

Data Index: 70380 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.1593. Min Act: -0.1700

Data Index: 194616 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.1593. Min Act: -0.1700

Data Index: 591338 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.1750. Min Act: -0.1700

Data Index: 210353 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.1278. Min Act: -0.1700

Data Index: 1345818 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.1278. Min Act: -0.1700

Data Index: 906545 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.1278. Min Act: -0.1700

Data Index: 492933 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.1120. Min Act: -0.1700

Data Index: 734943 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.1120. Min Act: -0.1700

Data Index: 956308 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.0963. Min Act: -0.1700

Data Index: 625077 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.0963. Min Act: -0.1700

Data Index: 570994 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.0805. Min Act: -0.1700

Data Index: 1338984 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.0805. Min Act: -0.1700

Data Index: 1170372 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.0647. Min Act: -0.1700

Data Index: 1044951 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.0805. Min Act: -0.1700

Data Index: 1233685 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.0647. Min Act: -0.1700

Data Index: 947107 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 3.2380. Min Range: -3.2380

Max Act: 3.0647. Min Act: -0.1700

Data Index: 1229611 (C4 (Web Text))

Max Activating Token Index: 256