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

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

Neuron 875 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.1503. Min Act: -0.1700

Data Index: 734252 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.1346. Min Act: -0.1700

Data Index: 804528 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.1346. Min Act: -0.1700

Data Index: 894600 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.1188. Min Act: -0.1700

Data Index: 775343 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.1346. Min Act: -0.1700

Data Index: 1013790 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.1188. Min Act: -0.1700

Data Index: 745534 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.1031. Min Act: -0.1700

Data Index: 503783 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.0873. Min Act: -0.1700

Data Index: 546021 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.0873. Min Act: -0.1700

Data Index: 1080473 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.0873. Min Act: -0.1700

Data Index: 1224992 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.0873. Min Act: -0.1700

Data Index: 788475 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.0715. Min Act: -0.1700

Data Index: 1596262 (Python Code)

Max Activating Token Index: 763

Text #12

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.0873. Min Act: -0.1700

Data Index: 428964 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.0715. Min Act: -0.1700

Data Index: 515620 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.0715. Min Act: -0.1700

Data Index: 112685 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.0558. Min Act: -0.1700

Data Index: 525614 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.0715. Min Act: -0.1700

Data Index: 987862 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.0558. Min Act: -0.1700

Data Index: 488935 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.0715. Min Act: -0.1700

Data Index: 572272 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 3.1503. Min Range: -3.1503

Max Act: 3.0242. Min Act: -0.1700

Data Index: 571136 (C4 (Web Text))

Max Activating Token Index: 797