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

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

Neuron 964 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: 3.8692. Min Range: -3.8692

Max Act: 3.8692. Min Act: -0.1700

Data Index: 332319 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.8379. Min Act: -0.1700

Data Index: 954391 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7440. Min Act: -0.1700

Data Index: 367759 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7440. Min Act: -0.1700

Data Index: 597 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7128. Min Act: -0.1700

Data Index: 739900 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7128. Min Act: -0.1700

Data Index: 965724 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7128. Min Act: -0.1700

Data Index: 984016 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7128. Min Act: -0.1700

Data Index: 1068324 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7128. Min Act: -0.1700

Data Index: 733593 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7128. Min Act: -0.1700

Data Index: 488786 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7128. Min Act: -0.1700

Data Index: 684401 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7128. Min Act: -0.1700

Data Index: 55104 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.6502. Min Act: -0.1700

Data Index: 1038010 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.6502. Min Act: -0.1700

Data Index: 1252947 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.6502. Min Act: -0.1700

Data Index: 1076821 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.6502. Min Act: -0.1700

Data Index: 547629 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.6189. Min Act: -0.1700

Data Index: 778210 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.6502. Min Act: -0.1700

Data Index: 271461 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.6815. Min Act: -0.1700

Data Index: 479915 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.6815. Min Act: -0.1700

Data Index: 169601 (C4 (Web Text))

Max Activating Token Index: 277