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

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

Neuron 1923 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0340. Min Range: -4.0340

Max Act: 4.0340. Min Act: -0.1700

Data Index: 844099 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.7525. Min Act: -0.1700

Data Index: 21382 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.7212. Min Act: -0.1700

Data Index: 1164533 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.7525. Min Act: -0.1700

Data Index: 1113740 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.7212. Min Act: -0.1700

Data Index: 629410 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.7525. Min Act: -0.1700

Data Index: 837872 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.6586. Min Act: -0.1700

Data Index: 1349854 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.6899. Min Act: -0.1700

Data Index: 286026 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.7212. Min Act: -0.1700

Data Index: 1291852 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.5960. Min Act: -0.1700

Data Index: 59522 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.6273. Min Act: -0.1700

Data Index: 1179505 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.5960. Min Act: -0.1700

Data Index: 1606657 (Python Code)

Max Activating Token Index: 173

Text #12

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.5960. Min Act: -0.1700

Data Index: 587362 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.5334. Min Act: -0.1699

Data Index: 78821 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.5334. Min Act: -0.1700

Data Index: 1144978 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.5021. Min Act: -0.1700

Data Index: 883833 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.5021. Min Act: -0.1700

Data Index: 692925 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.5021. Min Act: -0.1700

Data Index: 277976 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.5021. Min Act: -0.1700

Data Index: 347140 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.5021. Min Act: -0.1699

Data Index: 1056142 (C4 (Web Text))

Max Activating Token Index: 731