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

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

Neuron 1841 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: 4.1202. Min Range: -4.1202

Max Act: 4.1202. Min Act: -0.1700

Data Index: 605092 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 4.1202. Min Range: -4.1202

Max Act: 4.0183. Min Act: -0.1700

Data Index: 1381726 (Python Code)

Max Activating Token Index: 356

Text #2

Max Range: 4.1202. Min Range: -4.1202

Max Act: 4.0102. Min Act: -0.1700

Data Index: 1283968 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.9628. Min Act: -0.1700

Data Index: 1332725 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.9553. Min Act: -0.1700

Data Index: 492642 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.9113. Min Act: -0.1700

Data Index: 822713 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.9438. Min Act: -0.1700

Data Index: 394014 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.9095. Min Act: -0.1700

Data Index: 221385 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.8911. Min Act: -0.1700

Data Index: 1104727 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.8754. Min Act: -0.1700

Data Index: 578736 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.8827. Min Act: -0.1700

Data Index: 1332933 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.8251. Min Act: -0.1700

Data Index: 478755 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.8110. Min Act: -0.1700

Data Index: 500578 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.8344. Min Act: -0.1700

Data Index: 29848 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.8198. Min Act: -0.1700

Data Index: 648076 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.8279. Min Act: -0.1700

Data Index: 1052277 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.8011. Min Act: -0.1700

Data Index: 348506 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.7950. Min Act: -0.1700

Data Index: 274382 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.7680. Min Act: -0.1700

Data Index: 148080 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.7642. Min Act: -0.1700

Data Index: 928998 (C4 (Web Text))

Max Activating Token Index: 938