Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1388 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.1745. Min Range: -4.1745

Max Act: 4.1745. Min Act: -0.1700

Data Index: 622432 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.9869. Min Act: -0.1700

Data Index: 666529 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.9713. Min Act: -0.1700

Data Index: 843648 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.9400. Min Act: -0.1700

Data Index: 1345780 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.9244. Min Act: -0.1700

Data Index: 1306552 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.8306. Min Act: -0.1700

Data Index: 81725 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.8462. Min Act: -0.1700

Data Index: 808115 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.8149. Min Act: -0.1700

Data Index: 1286724 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.8149. Min Act: -0.1700

Data Index: 986340 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.8149. Min Act: -0.1700

Data Index: 855829 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.7680. Min Act: -0.1700

Data Index: 731778 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.7680. Min Act: -0.1700

Data Index: 926477 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.7367. Min Act: -0.1700

Data Index: 757681 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.7837. Min Act: -0.1700

Data Index: 544731 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.7524. Min Act: -0.1700

Data Index: 1317974 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.7524. Min Act: -0.1700

Data Index: 419001 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.7367. Min Act: -0.1700

Data Index: 911924 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.7211. Min Act: -0.1699

Data Index: 565279 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.7367. Min Act: -0.1700

Data Index: 1106869 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.7367. Min Act: -0.1700

Data Index: 1206091 (C4 (Web Text))

Max Activating Token Index: 794