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

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

Neuron 102 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: 3.2776. Min Range: -3.2776

Max Act: 3.2776. Min Act: -0.1700

Data Index: 1318149 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 3.2776. Min Range: -3.2776

Max Act: 3.1977. Min Act: -0.1700

Data Index: 124017 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 3.2776. Min Range: -3.2776

Max Act: 3.2141. Min Act: -0.1700

Data Index: 1188568 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 3.2776. Min Range: -3.2776

Max Act: 3.0500. Min Act: -0.1700

Data Index: 426200 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 3.2776. Min Range: -3.2776

Max Act: 3.0522. Min Act: -0.1700

Data Index: 1273638 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 3.2776. Min Range: -3.2776

Max Act: 3.0350. Min Act: -0.1700

Data Index: 413640 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 3.2776. Min Range: -3.2776

Max Act: 3.0419. Min Act: -0.1699

Data Index: 171404 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 3.2776. Min Range: -3.2776

Max Act: 3.0257. Min Act: -0.1700

Data Index: 411073 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 3.2776. Min Range: -3.2776

Max Act: 2.9883. Min Act: -0.1700

Data Index: 588505 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 3.2776. Min Range: -3.2776

Max Act: 2.9831. Min Act: -0.1700

Data Index: 1634189 (Python Code)

Max Activating Token Index: 766

Text #10

Max Range: 3.2776. Min Range: -3.2776

Max Act: 2.9811. Min Act: -0.1700

Data Index: 283042 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 3.2776. Min Range: -3.2776

Max Act: 2.9857. Min Act: -0.1700

Data Index: 532741 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 3.2776. Min Range: -3.2776

Max Act: 2.9646. Min Act: -0.1700

Data Index: 964612 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 3.2776. Min Range: -3.2776

Max Act: 2.9728. Min Act: -0.1700

Data Index: 830436 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 3.2776. Min Range: -3.2776

Max Act: 2.9592. Min Act: -0.1700

Data Index: 572724 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 3.2776. Min Range: -3.2776

Max Act: 2.9294. Min Act: -0.1700

Data Index: 774738 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 3.2776. Min Range: -3.2776

Max Act: 2.9538. Min Act: -0.1700

Data Index: 972227 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 3.2776. Min Range: -3.2776

Max Act: 2.9497. Min Act: -0.1700

Data Index: 565972 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 3.2776. Min Range: -3.2776

Max Act: 2.9401. Min Act: -0.1700

Data Index: 883146 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 3.2776. Min Range: -3.2776

Max Act: 2.9520. Min Act: -0.1700

Data Index: 941261 (C4 (Web Text))

Max Activating Token Index: 74