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

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

Neuron 1034 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: 5.3494. Min Range: -5.3494

Max Act: 5.3494. Min Act: -0.1700

Data Index: 379832 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 5.3494. Min Range: -5.3494

Max Act: 5.2869. Min Act: -0.1700

Data Index: 1121566 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 5.3494. Min Range: -5.3494

Max Act: 5.2557. Min Act: -0.1700

Data Index: 303386 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 5.3494. Min Range: -5.3494

Max Act: 5.1619. Min Act: -0.1700

Data Index: 1147842 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 5.3494. Min Range: -5.3494

Max Act: 5.0994. Min Act: -0.1700

Data Index: 20267 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 5.3494. Min Range: -5.3494

Max Act: 5.1619. Min Act: -0.1700

Data Index: 314035 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 5.3494. Min Range: -5.3494

Max Act: 5.1619. Min Act: -0.1700

Data Index: 1208510 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 5.3494. Min Range: -5.3494

Max Act: 5.0369. Min Act: -0.1700

Data Index: 410563 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 5.3494. Min Range: -5.3494

Max Act: 5.0994. Min Act: -0.1700

Data Index: 1161585 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 5.3494. Min Range: -5.3494

Max Act: 5.1619. Min Act: -0.1699

Data Index: 312974 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 5.3494. Min Range: -5.3494

Max Act: 5.0369. Min Act: -0.1700

Data Index: 1249499 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 5.3494. Min Range: -5.3494

Max Act: 5.0682. Min Act: -0.1700

Data Index: 80731 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 5.3494. Min Range: -5.3494

Max Act: 5.0369. Min Act: -0.1700

Data Index: 570228 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 5.3494. Min Range: -5.3494

Max Act: 5.0682. Min Act: -0.1700

Data Index: 727400 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 5.3494. Min Range: -5.3494

Max Act: 5.0369. Min Act: -0.1700

Data Index: 1302880 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 5.3494. Min Range: -5.3494

Max Act: 5.0682. Min Act: -0.1700

Data Index: 746692 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 5.3494. Min Range: -5.3494

Max Act: 5.0057. Min Act: -0.1699

Data Index: 584611 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 5.3494. Min Range: -5.3494

Max Act: 5.0369. Min Act: -0.1700

Data Index: 603299 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 5.3494. Min Range: -5.3494

Max Act: 5.0057. Min Act: -0.1699

Data Index: 992789 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 5.3494. Min Range: -5.3494

Max Act: 5.0369. Min Act: -0.1700

Data Index: 442897 (C4 (Web Text))

Max Activating Token Index: 537