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

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

Neuron 130 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: 3.4519. Min Range: -3.4519

Max Act: 3.4519. Min Act: -0.1700

Data Index: 518921 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.3891. Min Act: -0.1700

Data Index: 580492 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.3735. Min Act: -0.1700

Data Index: 504168 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.3421. Min Act: -0.1700

Data Index: 858098 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.3264. Min Act: -0.1700

Data Index: 837613 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.3264. Min Act: -0.1700

Data Index: 1128674 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.3421. Min Act: -0.1700

Data Index: 849475 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.3264. Min Act: -0.1700

Data Index: 1288409 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.3107. Min Act: -0.1700

Data Index: 116033 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.3107. Min Act: -0.1700

Data Index: 70717 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.2793. Min Act: -0.1700

Data Index: 39796 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.2793. Min Act: -0.1700

Data Index: 1409767 (Python Code)

Max Activating Token Index: 554

Text #12

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.2793. Min Act: -0.1700

Data Index: 264452 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.2635. Min Act: -0.1700

Data Index: 1153047 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.2321. Min Act: -0.1700

Data Index: 807417 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.2321. Min Act: -0.1700

Data Index: 66402 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.2478. Min Act: -0.1700

Data Index: 655679 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.2478. Min Act: -0.1700

Data Index: 838245 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.2478. Min Act: -0.1700

Data Index: 519977 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.2635. Min Act: -0.1700

Data Index: 175971 (C4 (Web Text))

Max Activating Token Index: 500