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

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

Neuron 659 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: 5.8041. Min Range: -5.8041

Max Act: 5.8041. Min Act: -0.1700

Data Index: 791969 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 5.8041. Min Range: -5.8041

Max Act: 5.6166. Min Act: -0.1700

Data Index: 747547 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 5.8041. Min Range: -5.8041

Max Act: 5.5854. Min Act: -0.1700

Data Index: 1353221 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 5.8041. Min Range: -5.8041

Max Act: 5.6166. Min Act: -0.1700

Data Index: 302140 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 5.8041. Min Range: -5.8041

Max Act: 5.6791. Min Act: -0.1700

Data Index: 378124 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 5.8041. Min Range: -5.8041

Max Act: 5.6166. Min Act: -0.1700

Data Index: 1188383 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 5.8041. Min Range: -5.8041

Max Act: 5.6166. Min Act: -0.1700

Data Index: 31409 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 5.8041. Min Range: -5.8041

Max Act: 5.6791. Min Act: -0.1700

Data Index: 50684 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 5.8041. Min Range: -5.8041

Max Act: 5.6166. Min Act: -0.1700

Data Index: 86189 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 5.8041. Min Range: -5.8041

Max Act: 5.5541. Min Act: -0.1700

Data Index: 688962 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 5.8041. Min Range: -5.8041

Max Act: 5.5541. Min Act: -0.1700

Data Index: 1267276 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 5.8041. Min Range: -5.8041

Max Act: 5.5229. Min Act: -0.1700

Data Index: 1302723 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 5.8041. Min Range: -5.8041

Max Act: 5.5854. Min Act: -0.1700

Data Index: 941983 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 5.8041. Min Range: -5.8041

Max Act: 5.5854. Min Act: -0.1700

Data Index: 1040009 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 5.8041. Min Range: -5.8041

Max Act: 5.5229. Min Act: -0.1700

Data Index: 168583 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 5.8041. Min Range: -5.8041

Max Act: 5.5229. Min Act: -0.1700

Data Index: 443150 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 5.8041. Min Range: -5.8041

Max Act: 5.5854. Min Act: -0.1700

Data Index: 1218777 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 5.8041. Min Range: -5.8041

Max Act: 5.5854. Min Act: -0.1700

Data Index: 434158 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 5.8041. Min Range: -5.8041

Max Act: 5.5541. Min Act: -0.1700

Data Index: 1134408 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 5.8041. Min Range: -5.8041

Max Act: 5.5541. Min Act: -0.1700

Data Index: 820429 (C4 (Web Text))

Max Activating Token Index: 224