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

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

Neuron 1213 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.6081. Min Act: -0.1700

Data Index: 392864 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.6393. Min Act: -0.1700

Data Index: 627184 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.4831. Min Act: -0.1700

Data Index: 897172 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.5768. Min Act: -0.1700

Data Index: 612283 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.4518. Min Act: -0.1700

Data Index: 474475 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.4831. Min Act: -0.1700

Data Index: 458886 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.4831. Min Act: -0.1700

Data Index: 1349013 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.5143. Min Act: -0.1700

Data Index: 829199 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.5456. Min Act: -0.1700

Data Index: 3883 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.5143. Min Act: -0.1700

Data Index: 936626 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.5768. Min Act: -0.1700

Data Index: 186699 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.5143. Min Act: -0.1700

Data Index: 907934 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.4831. Min Act: -0.1700

Data Index: 654880 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.5456. Min Act: -0.1700

Data Index: 1298996 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.4206. Min Act: -0.1700

Data Index: 956891 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.3581. Min Act: -0.1700

Data Index: 1239717 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.3893. Min Act: -0.1700

Data Index: 597597 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.4518. Min Act: -0.1700

Data Index: 743061 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.4831. Min Act: -0.1700

Data Index: 1171582 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 5.6393. Min Range: -5.6393

Max Act: 5.4206. Min Act: -0.1700

Data Index: 974383 (C4 (Web Text))

Max Activating Token Index: 581