Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1918 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.0160. Min Range: -4.0160

Max Act: 4.0160. Min Act: -0.1700

Data Index: 1261513 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 4.0160. Min Range: -4.0160

Max Act: 3.9847. Min Act: -0.1700

Data Index: 616070 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 4.0160. Min Range: -4.0160

Max Act: 3.9378. Min Act: -0.1700

Data Index: 1281212 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 4.0160. Min Range: -4.0160

Max Act: 3.8753. Min Act: -0.1700

Data Index: 678837 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 4.0160. Min Range: -4.0160

Max Act: 3.8596. Min Act: -0.1700

Data Index: 334385 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 4.0160. Min Range: -4.0160

Max Act: 3.8753. Min Act: -0.1699

Data Index: 11280 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 4.0160. Min Range: -4.0160

Max Act: 3.8127. Min Act: -0.1700

Data Index: 989380 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 4.0160. Min Range: -4.0160

Max Act: 3.8284. Min Act: -0.1700

Data Index: 1188192 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 4.0160. Min Range: -4.0160

Max Act: 3.8909. Min Act: -0.1700

Data Index: 642128 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 4.0160. Min Range: -4.0160

Max Act: 3.8284. Min Act: -0.1700

Data Index: 341696 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 4.0160. Min Range: -4.0160

Max Act: 3.8284. Min Act: -0.1700

Data Index: 595898 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 4.0160. Min Range: -4.0160

Max Act: 3.8440. Min Act: -0.1700

Data Index: 1156983 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 4.0160. Min Range: -4.0160

Max Act: 3.8440. Min Act: -0.1700

Data Index: 1314207 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 4.0160. Min Range: -4.0160

Max Act: 3.8127. Min Act: -0.1699

Data Index: 1109012 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 4.0160. Min Range: -4.0160

Max Act: 3.8127. Min Act: -0.1700

Data Index: 1154500 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 4.0160. Min Range: -4.0160

Max Act: 3.8127. Min Act: -0.1700

Data Index: 444271 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 4.0160. Min Range: -4.0160

Max Act: 3.8127. Min Act: -0.1700

Data Index: 1273929 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 4.0160. Min Range: -4.0160

Max Act: 3.7971. Min Act: -0.1700

Data Index: 467149 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 4.0160. Min Range: -4.0160

Max Act: 3.8127. Min Act: -0.1700

Data Index: 1195647 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 4.0160. Min Range: -4.0160

Max Act: 3.8127. Min Act: -0.1700

Data Index: 488218 (C4 (Web Text))

Max Activating Token Index: 723