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

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

Neuron 1973 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: 5.2200. Min Range: -5.2200

Max Act: 5.2200. Min Act: -0.1700

Data Index: 747598 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 5.2200. Min Range: -5.2200

Max Act: 5.1263. Min Act: -0.1700

Data Index: 616664 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 5.2200. Min Range: -5.2200

Max Act: 5.1263. Min Act: -0.1700

Data Index: 708975 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 5.2200. Min Range: -5.2200

Max Act: 5.0950. Min Act: -0.1700

Data Index: 553966 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 5.2200. Min Range: -5.2200

Max Act: 5.0638. Min Act: -0.1700

Data Index: 1259943 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 5.2200. Min Range: -5.2200

Max Act: 5.0638. Min Act: -0.1700

Data Index: 1170364 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 5.2200. Min Range: -5.2200

Max Act: 5.0638. Min Act: -0.1700

Data Index: 685620 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 5.2200. Min Range: -5.2200

Max Act: 5.0638. Min Act: -0.1700

Data Index: 901923 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 5.2200. Min Range: -5.2200

Max Act: 4.9700. Min Act: -0.1700

Data Index: 497764 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 5.2200. Min Range: -5.2200

Max Act: 5.0638. Min Act: -0.1700

Data Index: 270233 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 5.2200. Min Range: -5.2200

Max Act: 4.8763. Min Act: -0.1700

Data Index: 1128426 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 5.2200. Min Range: -5.2200

Max Act: 4.9700. Min Act: -0.1700

Data Index: 868360 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 5.2200. Min Range: -5.2200

Max Act: 5.0013. Min Act: -0.1700

Data Index: 701115 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 5.2200. Min Range: -5.2200

Max Act: 4.9700. Min Act: -0.1700

Data Index: 270074 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 5.2200. Min Range: -5.2200

Max Act: 4.9700. Min Act: -0.1700

Data Index: 1102903 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 5.2200. Min Range: -5.2200

Max Act: 4.9700. Min Act: -0.1700

Data Index: 1165042 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 5.2200. Min Range: -5.2200

Max Act: 4.9075. Min Act: -0.1700

Data Index: 510280 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 5.2200. Min Range: -5.2200

Max Act: 4.8763. Min Act: -0.1700

Data Index: 511214 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 5.2200. Min Range: -5.2200

Max Act: 4.9075. Min Act: -0.1700

Data Index: 973087 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 5.2200. Min Range: -5.2200

Max Act: 4.9388. Min Act: -0.1700

Data Index: 850111 (C4 (Web Text))

Max Activating Token Index: 917