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

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

Neuron 30 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: 3.5093. Min Range: -3.5093

Max Act: 3.5093. Min Act: -0.1700

Data Index: 1127478 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 3.5093. Min Range: -3.5093

Max Act: 3.4079. Min Act: -0.1700

Data Index: 1267665 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 3.5093. Min Range: -3.5093

Max Act: 3.3717. Min Act: -0.1700

Data Index: 1099782 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 3.5093. Min Range: -3.5093

Max Act: 3.3582. Min Act: -0.1700

Data Index: 11366 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 3.5093. Min Range: -3.5093

Max Act: 3.3187. Min Act: -0.1700

Data Index: 518271 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 3.5093. Min Range: -3.5093

Max Act: 3.3114. Min Act: -0.1700

Data Index: 755117 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 3.5093. Min Range: -3.5093

Max Act: 3.3003. Min Act: -0.1700

Data Index: 884155 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 3.5093. Min Range: -3.5093

Max Act: 3.2917. Min Act: -0.1700

Data Index: 1045627 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 3.5093. Min Range: -3.5093

Max Act: 3.2199. Min Act: -0.1699

Data Index: 725391 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 3.5093. Min Range: -3.5093

Max Act: 3.2366. Min Act: -0.1700

Data Index: 747538 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 3.5093. Min Range: -3.5093

Max Act: 3.2384. Min Act: -0.1700

Data Index: 472373 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 3.5093. Min Range: -3.5093

Max Act: 3.2235. Min Act: -0.1696

Data Index: 1260667 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 3.5093. Min Range: -3.5093

Max Act: 3.1765. Min Act: -0.1700

Data Index: 449993 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 3.5093. Min Range: -3.5093

Max Act: 3.1705. Min Act: -0.1700

Data Index: 191369 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 3.5093. Min Range: -3.5093

Max Act: 3.1669. Min Act: -0.1700

Data Index: 724183 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 3.5093. Min Range: -3.5093

Max Act: 3.1723. Min Act: -0.1700

Data Index: 1039782 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 3.5093. Min Range: -3.5093

Max Act: 3.1682. Min Act: -0.1700

Data Index: 638338 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 3.5093. Min Range: -3.5093

Max Act: 3.1604. Min Act: -0.1700

Data Index: 1133993 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 3.5093. Min Range: -3.5093

Max Act: 3.1532. Min Act: -0.1699

Data Index: 1181447 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 3.5093. Min Range: -3.5093

Max Act: 3.1582. Min Act: -0.1700

Data Index: 282139 (C4 (Web Text))

Max Activating Token Index: 760