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

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

Neuron 1596 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: 3.2173. Min Range: -3.2173

Max Act: 3.2173. Min Act: -0.1700

Data Index: 627545 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 3.2173. Min Range: -3.2173

Max Act: 3.1637. Min Act: -0.1700

Data Index: 1084851 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 3.2173. Min Range: -3.2173

Max Act: 3.1398. Min Act: -0.1700

Data Index: 1131208 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 3.2173. Min Range: -3.2173

Max Act: 3.0620. Min Act: -0.1700

Data Index: 874054 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 3.2173. Min Range: -3.2173

Max Act: 3.0703. Min Act: -0.1699

Data Index: 1212103 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 3.2173. Min Range: -3.2173

Max Act: 3.0562. Min Act: -0.1700

Data Index: 843492 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 3.2173. Min Range: -3.2173

Max Act: 3.0339. Min Act: -0.1700

Data Index: 271623 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 3.2173. Min Range: -3.2173

Max Act: 3.0344. Min Act: -0.1700

Data Index: 201775 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 3.2173. Min Range: -3.2173

Max Act: 3.0076. Min Act: -0.1700

Data Index: 182114 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 3.2173. Min Range: -3.2173

Max Act: 2.9903. Min Act: -0.1574

Data Index: 1067252 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 3.2173. Min Range: -3.2173

Max Act: 2.9987. Min Act: -0.1700

Data Index: 990343 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 3.2173. Min Range: -3.2173

Max Act: 2.9932. Min Act: -0.1700

Data Index: 1036843 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 3.2173. Min Range: -3.2173

Max Act: 3.0029. Min Act: -0.1697

Data Index: 566966 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 3.2173. Min Range: -3.2173

Max Act: 3.0086. Min Act: -0.1700

Data Index: 580182 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 3.2173. Min Range: -3.2173

Max Act: 2.9560. Min Act: -0.1700

Data Index: 258291 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 3.2173. Min Range: -3.2173

Max Act: 2.9618. Min Act: -0.1700

Data Index: 275661 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 3.2173. Min Range: -3.2173

Max Act: 2.9568. Min Act: -0.1700

Data Index: 998219 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 3.2173. Min Range: -3.2173

Max Act: 2.9563. Min Act: -0.1700

Data Index: 89209 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 3.2173. Min Range: -3.2173

Max Act: 2.9714. Min Act: -0.1700

Data Index: 774932 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 3.2173. Min Range: -3.2173

Max Act: 2.9738. Min Act: -0.1700

Data Index: 848620 (C4 (Web Text))

Max Activating Token Index: 666