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

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

Neuron 1340 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: 5.1536. Min Range: -5.1536

Max Act: 5.1536. Min Act: -0.1700

Data Index: 300467 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.9974. Min Act: -0.1700

Data Index: 1158018 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.8099. Min Act: -0.1700

Data Index: 558215 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.7474. Min Act: -0.1700

Data Index: 908906 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.7474. Min Act: -0.1700

Data Index: 484503 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.7161. Min Act: -0.1700

Data Index: 752193 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.6224. Min Act: -0.1700

Data Index: 759704 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.6536. Min Act: -0.1700

Data Index: 538378 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.6536. Min Act: -0.1700

Data Index: 416265 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.5599. Min Act: -0.1700

Data Index: 378182 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.5911. Min Act: -0.1699

Data Index: 565675 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.5911. Min Act: -0.1700

Data Index: 712445 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.5911. Min Act: -0.1700

Data Index: 415025 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.6224. Min Act: -0.1700

Data Index: 298593 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.6536. Min Act: -0.1700

Data Index: 1132197 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.5599. Min Act: -0.1700

Data Index: 514790 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.6224. Min Act: -0.1700

Data Index: 1183317 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.6224. Min Act: -0.1699

Data Index: 575959 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.5599. Min Act: -0.1700

Data Index: 890676 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.5599. Min Act: -0.1700

Data Index: 595333 (C4 (Web Text))

Max Activating Token Index: 279