Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1812 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.0504. Min Range: -3.0504

Max Act: 3.0504. Min Act: -0.1700

Data Index: 312981 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.9530. Min Act: -0.1699

Data Index: 750758 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.9591. Min Act: -0.1700

Data Index: 305585 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.9669. Min Act: -0.1700

Data Index: 821983 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.9202. Min Act: -0.1700

Data Index: 103613 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.9042. Min Act: -0.1699

Data Index: 73663 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8860. Min Act: -0.1700

Data Index: 1096759 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8848. Min Act: -0.1700

Data Index: 60241 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8687. Min Act: -0.1699

Data Index: 624433 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8522. Min Act: -0.1699

Data Index: 1252693 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8687. Min Act: -0.1700

Data Index: 1180895 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8716. Min Act: -0.1700

Data Index: 501114 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8541. Min Act: -0.1700

Data Index: 854001 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8486. Min Act: -0.1700

Data Index: 215 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8233. Min Act: -0.1700

Data Index: 1055137 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8232. Min Act: -0.1698

Data Index: 309188 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8291. Min Act: -0.1699

Data Index: 77875 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8332. Min Act: -0.1700

Data Index: 521524 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8368. Min Act: -0.1700

Data Index: 812398 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8343. Min Act: -0.1700

Data Index: 1313482 (C4 (Web Text))

Max Activating Token Index: 837