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

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

Neuron 1683 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: 3.4137. Min Range: -3.4137

Max Act: 3.4007. Min Act: -0.1700

Data Index: 1040870 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.4137. Min Act: -0.1675

Data Index: 1032869 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.3891. Min Act: -0.1698

Data Index: 349268 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.3700. Min Act: -0.1700

Data Index: 379772 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.3336. Min Act: -0.1691

Data Index: 831327 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.3138. Min Act: -0.1700

Data Index: 696594 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.3137. Min Act: -0.1700

Data Index: 49652 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.3134. Min Act: -0.1669

Data Index: 914266 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.3153. Min Act: -0.1699

Data Index: 262374 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.3245. Min Act: -0.1698

Data Index: 249498 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.3093. Min Act: -0.1699

Data Index: 867388 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.3263. Min Act: -0.1700

Data Index: 1060705 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.2655. Min Act: -0.1690

Data Index: 918075 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.2763. Min Act: -0.1698

Data Index: 52136 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.2852. Min Act: -0.1697

Data Index: 1107784 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.2579. Min Act: -0.1700

Data Index: 7610 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.2619. Min Act: -0.1700

Data Index: 191037 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.2454. Min Act: -0.1687

Data Index: 693297 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.2465. Min Act: -0.1697

Data Index: 991826 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.2438. Min Act: -0.1671

Data Index: 868796 (C4 (Web Text))

Max Activating Token Index: 866