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

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

Neuron 2029 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: 3.8304. Min Range: -3.8304

Max Act: 3.8304. Min Act: -0.1700

Data Index: 1172731 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.6851. Min Act: -0.1700

Data Index: 754774 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.7012. Min Act: -0.1700

Data Index: 968887 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.6534. Min Act: -0.1700

Data Index: 781508 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.6120. Min Act: -0.1700

Data Index: 539418 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.5388. Min Act: -0.1700

Data Index: 297482 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.5572. Min Act: -0.1700

Data Index: 745803 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.5264. Min Act: -0.1700

Data Index: 364246 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.5236. Min Act: -0.1700

Data Index: 608445 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.5162. Min Act: -0.1700

Data Index: 1162514 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.4931. Min Act: -0.1700

Data Index: 1024070 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.5132. Min Act: -0.1700

Data Index: 93623 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.5186. Min Act: -0.1700

Data Index: 1534813 (Python Code)

Max Activating Token Index: 150

Text #13

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.5033. Min Act: -0.1700

Data Index: 1574177 (Python Code)

Max Activating Token Index: 1003

Text #14

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.5014. Min Act: -0.1700

Data Index: 1080895 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.4863. Min Act: -0.1700

Data Index: 797628 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.4703. Min Act: -0.1700

Data Index: 421712 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.4809. Min Act: -0.1700

Data Index: 726118 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.4589. Min Act: -0.1700

Data Index: 962525 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.4429. Min Act: -0.1700

Data Index: 1589170 (Python Code)

Max Activating Token Index: 759