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

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

Neuron 1507 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1314. Min Range: -5.1314

Max Act: 5.1314. Min Act: -0.1700

Data Index: 792613 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 5.1314. Min Range: -5.1314

Max Act: 5.1314. Min Act: -0.1700

Data Index: 1167188 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.8814. Min Act: -0.1700

Data Index: 506114 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.8814. Min Act: -0.1700

Data Index: 740982 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.8502. Min Act: -0.1700

Data Index: 434779 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.8502. Min Act: -0.1700

Data Index: 897370 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.9439. Min Act: -0.1700

Data Index: 401590 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.8814. Min Act: -0.1700

Data Index: 592037 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.8189. Min Act: -0.1700

Data Index: 219509 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.8189. Min Act: -0.1700

Data Index: 143241 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.8502. Min Act: -0.1700

Data Index: 1305146 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.8189. Min Act: -0.1700

Data Index: 1277217 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.7564. Min Act: -0.1700

Data Index: 389212 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.7564. Min Act: -0.1700

Data Index: 89468 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.7564. Min Act: -0.1700

Data Index: 658793 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.7564. Min Act: -0.1700

Data Index: 74539 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.7564. Min Act: -0.1700

Data Index: 132553 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.7252. Min Act: -0.1700

Data Index: 1004926 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.7564. Min Act: -0.1700

Data Index: 414503 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.7564. Min Act: -0.1700

Data Index: 1143224 (C4 (Web Text))

Max Activating Token Index: 298