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

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

Neuron 406 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: 5.8369. Min Range: -5.8369

Max Act: 5.8369. Min Act: 0.5905

Data Index: 320560 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 5.8369. Min Range: -5.8369

Max Act: 5.3279. Min Act: -0.0434

Data Index: 68844 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 5.8369. Min Range: -5.8369

Max Act: 5.2651. Min Act: -0.1697

Data Index: 16816 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 5.8369. Min Range: -5.8369

Max Act: 5.2756. Min Act: -0.1669

Data Index: 760132 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 5.8369. Min Range: -5.8369

Max Act: 5.2642. Min Act: -0.1699

Data Index: 14843 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 5.8369. Min Range: -5.8369

Max Act: 5.2349. Min Act: -0.0937

Data Index: 843485 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 5.8369. Min Range: -5.8369

Max Act: 5.1360. Min Act: 0.1172

Data Index: 1453549 (Python Code)

Max Activating Token Index: 638

Text #7

Max Range: 5.8369. Min Range: -5.8369

Max Act: 5.1635. Min Act: 0.1641

Data Index: 1587017 (Python Code)

Max Activating Token Index: 225

Text #8

Max Range: 5.8369. Min Range: -5.8369

Max Act: 5.1426. Min Act: -0.1662

Data Index: 547288 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 5.8369. Min Range: -5.8369

Max Act: 5.1128. Min Act: -0.1647

Data Index: 428810 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 5.8369. Min Range: -5.8369

Max Act: 5.0944. Min Act: -0.1699

Data Index: 923142 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 5.8369. Min Range: -5.8369

Max Act: 5.0618. Min Act: -0.1699

Data Index: 821575 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 5.8369. Min Range: -5.8369

Max Act: 5.0588. Min Act: 0.4954

Data Index: 1183635 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 5.8369. Min Range: -5.8369

Max Act: 5.0544. Min Act: 0.0631

Data Index: 1582571 (Python Code)

Max Activating Token Index: 837

Text #14

Max Range: 5.8369. Min Range: -5.8369

Max Act: 5.0659. Min Act: -0.1699

Data Index: 1390334 (Python Code)

Max Activating Token Index: 326

Text #15

Max Range: 5.8369. Min Range: -5.8369

Max Act: 5.0329. Min Act: 0.0691

Data Index: 1573998 (Python Code)

Max Activating Token Index: 223

Text #16

Max Range: 5.8369. Min Range: -5.8369

Max Act: 5.0265. Min Act: 0.0830

Data Index: 1597276 (Python Code)

Max Activating Token Index: 765

Text #17

Max Range: 5.8369. Min Range: -5.8369

Max Act: 5.0417. Min Act: -0.1526

Data Index: 6083 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 5.8369. Min Range: -5.8369

Max Act: 5.0089. Min Act: -0.1700

Data Index: 658188 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 5.8369. Min Range: -5.8369

Max Act: 5.0030. Min Act: -0.1566

Data Index: 1309286 (C4 (Web Text))

Max Activating Token Index: 526