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

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

Neuron 967 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.3654. Min Act: -0.1700

Data Index: 223401 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.3026. Min Act: -0.1700

Data Index: 960668 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.2712. Min Act: -0.1700

Data Index: 313031 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.2555. Min Act: -0.1700

Data Index: 1098203 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.2555. Min Act: -0.1700

Data Index: 24617 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.2241. Min Act: -0.1699

Data Index: 1279227 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.2398. Min Act: -0.1700

Data Index: 548655 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.2241. Min Act: -0.1700

Data Index: 1110151 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.2241. Min Act: -0.1700

Data Index: 643993 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.2241. Min Act: -0.1700

Data Index: 1222383 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.2083. Min Act: -0.1700

Data Index: 1054511 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1926. Min Act: -0.1700

Data Index: 944948 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1611. Min Act: -0.1700

Data Index: 1123712 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1769. Min Act: -0.1700

Data Index: 610415 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1769. Min Act: -0.1700

Data Index: 1217357 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1611. Min Act: -0.1700

Data Index: 1212624 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1611. Min Act: -0.1700

Data Index: 1237681 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1296. Min Act: -0.1700

Data Index: 262832 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1611. Min Act: -0.1700

Data Index: 1118129 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1611. Min Act: -0.1700

Data Index: 125340 (C4 (Web Text))

Max Activating Token Index: 862