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

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

Neuron 1056 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: 5.0801. Min Range: -5.0801

Max Act: 5.0801. Min Act: -0.1700

Data Index: 958459 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 5.0801. Min Range: -5.0801

Max Act: 5.0488. Min Act: -0.1700

Data Index: 1101702 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 5.0801. Min Range: -5.0801

Max Act: 5.0488. Min Act: -0.1700

Data Index: 640691 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.9551. Min Act: -0.1700

Data Index: 787919 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 5.0801. Min Range: -5.0801

Max Act: 5.0488. Min Act: -0.1700

Data Index: 585378 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.9863. Min Act: -0.1700

Data Index: 404422 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.9551. Min Act: -0.1700

Data Index: 927380 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.9238. Min Act: -0.1700

Data Index: 105861 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.9551. Min Act: -0.1700

Data Index: 976187 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.9551. Min Act: -0.1700

Data Index: 1142636 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.9238. Min Act: -0.1700

Data Index: 684248 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.9238. Min Act: -0.1700

Data Index: 376733 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.9238. Min Act: -0.1700

Data Index: 254349 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.9551. Min Act: -0.1700

Data Index: 1232344 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.9551. Min Act: -0.1699

Data Index: 472090 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.8926. Min Act: -0.1700

Data Index: 514480 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.9238. Min Act: -0.1700

Data Index: 293487 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.9238. Min Act: -0.1700

Data Index: 954951 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.8926. Min Act: -0.1700

Data Index: 582666 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.9238. Min Act: -0.1700

Data Index: 627711 (C4 (Web Text))

Max Activating Token Index: 656