Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 179 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.7426. Min Act: -0.1700

Data Index: 270233 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.7113. Min Act: -0.1700

Data Index: 1439625 (Python Code)

Max Activating Token Index: 288

Text #2

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.7426. Min Act: -0.1700

Data Index: 730285 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.7113. Min Act: -0.1700

Data Index: 456326 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.7270. Min Act: -0.1700

Data Index: 211711 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.7270. Min Act: -0.1700

Data Index: 180848 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.6801. Min Act: -0.1700

Data Index: 424903 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.6801. Min Act: -0.1700

Data Index: 844058 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.6644. Min Act: -0.1700

Data Index: 204331 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.6487. Min Act: -0.1700

Data Index: 1205980 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.6801. Min Act: -0.1700

Data Index: 703000 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.6801. Min Act: -0.1700

Data Index: 547946 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.6331. Min Act: -0.1700

Data Index: 847950 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.6644. Min Act: -0.1700

Data Index: 964517 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.6331. Min Act: -0.1700

Data Index: 560657 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.6957. Min Act: -0.1700

Data Index: 1298691 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.6487. Min Act: -0.1700

Data Index: 243296 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.6487. Min Act: -0.1700

Data Index: 198187 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.6487. Min Act: -0.1700

Data Index: 758356 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.6174. Min Act: -0.1700

Data Index: 602221 (C4 (Web Text))

Max Activating Token Index: 180