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

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

Neuron 1888 in Layer 3

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: 5.1223. Min Act: -0.1700

Data Index: 570726 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 5.1536. Min Range: -5.1536

Max Act: 5.1536. Min Act: -0.1700

Data Index: 825054 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 5.1536. Min Range: -5.1536

Max Act: 5.1223. Min Act: -0.1700

Data Index: 814814 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 5.1536. Min Range: -5.1536

Max Act: 5.0598. Min Act: -0.1700

Data Index: 347652 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 5.1536. Min Range: -5.1536

Max Act: 5.0286. Min Act: -0.1700

Data Index: 34489 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 5.1536. Min Range: -5.1536

Max Act: 5.0598. Min Act: -0.1700

Data Index: 457425 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.9661. Min Act: -0.1700

Data Index: 72260 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 5.1536. Min Range: -5.1536

Max Act: 5.0286. Min Act: -0.1700

Data Index: 40060 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 5.1536. Min Range: -5.1536

Max Act: 5.0598. Min Act: -0.1700

Data Index: 135033 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 5.1536. Min Range: -5.1536

Max Act: 5.0911. Min Act: -0.1700

Data Index: 1022005 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 5.1536. Min Range: -5.1536

Max Act: 5.0286. Min Act: -0.1700

Data Index: 1320967 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.9661. Min Act: -0.1700

Data Index: 788441 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.9036. Min Act: -0.1700

Data Index: 40915 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.9661. Min Act: -0.1700

Data Index: 690432 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.9973. Min Act: -0.1700

Data Index: 119170 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.9661. Min Act: -0.1700

Data Index: 1055388 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.9661. Min Act: -0.1700

Data Index: 1281846 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.9036. Min Act: -0.1700

Data Index: 196994 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.9348. Min Act: -0.1700

Data Index: 32678 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 5.1536. Min Range: -5.1536

Max Act: 4.9036. Min Act: -0.1700

Data Index: 613087 (C4 (Web Text))

Max Activating Token Index: 193