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

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

Neuron 1769 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: 3.1464. Min Range: -3.1464

Max Act: 3.1464. Min Act: -0.1700

Data Index: 912925 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 3.1464. Min Range: -3.1464

Max Act: 3.1306. Min Act: -0.1700

Data Index: 81229 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 3.1464. Min Range: -3.1464

Max Act: 3.0675. Min Act: -0.1700

Data Index: 1107306 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 3.1464. Min Range: -3.1464

Max Act: 3.0833. Min Act: -0.1700

Data Index: 67840 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 3.1464. Min Range: -3.1464

Max Act: 3.0675. Min Act: -0.1700

Data Index: 1117210 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 3.1464. Min Range: -3.1464

Max Act: 3.0518. Min Act: -0.1700

Data Index: 824144 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 3.1464. Min Range: -3.1464

Max Act: 3.0675. Min Act: -0.1700

Data Index: 1215007 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 3.1464. Min Range: -3.1464

Max Act: 3.0675. Min Act: -0.1700

Data Index: 419838 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 3.1464. Min Range: -3.1464

Max Act: 3.0518. Min Act: -0.1700

Data Index: 928592 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 3.1464. Min Range: -3.1464

Max Act: 3.0360. Min Act: -0.1700

Data Index: 866846 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 3.1464. Min Range: -3.1464

Max Act: 3.0518. Min Act: -0.1700

Data Index: 270569 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 3.1464. Min Range: -3.1464

Max Act: 3.0518. Min Act: -0.1700

Data Index: 547483 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 3.1464. Min Range: -3.1464

Max Act: 3.0675. Min Act: -0.1700

Data Index: 183893 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 3.1464. Min Range: -3.1464

Max Act: 3.0518. Min Act: -0.1700

Data Index: 588404 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 3.1464. Min Range: -3.1464

Max Act: 3.0360. Min Act: -0.1700

Data Index: 53633 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 3.1464. Min Range: -3.1464

Max Act: 3.0360. Min Act: -0.1700

Data Index: 744297 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 3.1464. Min Range: -3.1464

Max Act: 3.0360. Min Act: -0.1700

Data Index: 421788 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 3.1464. Min Range: -3.1464

Max Act: 3.0360. Min Act: -0.1700

Data Index: 437395 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 3.1464. Min Range: -3.1464

Max Act: 3.0360. Min Act: -0.1700

Data Index: 773237 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 3.1464. Min Range: -3.1464

Max Act: 3.0202. Min Act: -0.1700

Data Index: 597857 (C4 (Web Text))

Max Activating Token Index: 921