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

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

Neuron 1788 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: 6.2671. Min Range: -6.2671

Max Act: 6.2400. Min Act: -0.1698

Data Index: 323914 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 6.2671. Min Range: -6.2671

Max Act: 6.2671. Min Act: -0.1261

Data Index: 1462279 (Python Code)

Max Activating Token Index: 578

Text #2

Max Range: 6.2671. Min Range: -6.2671

Max Act: 6.2082. Min Act: -0.1644

Data Index: 681161 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 6.2671. Min Range: -6.2671

Max Act: 6.1702. Min Act: -0.1699

Data Index: 1312657 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 6.2671. Min Range: -6.2671

Max Act: 6.1044. Min Act: -0.1700

Data Index: 1299100 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 6.2671. Min Range: -6.2671

Max Act: 6.1203. Min Act: -0.1671

Data Index: 400015 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 6.2671. Min Range: -6.2671

Max Act: 6.0568. Min Act: -0.1700

Data Index: 1356313 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 6.2671. Min Range: -6.2671

Max Act: 6.0649. Min Act: -0.1699

Data Index: 699708 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 6.2671. Min Range: -6.2671

Max Act: 6.0247. Min Act: -0.1669

Data Index: 1386160 (Python Code)

Max Activating Token Index: 107

Text #9

Max Range: 6.2671. Min Range: -6.2671

Max Act: 6.0167. Min Act: -0.1698

Data Index: 1618046 (Python Code)

Max Activating Token Index: 316

Text #10

Max Range: 6.2671. Min Range: -6.2671

Max Act: 5.9927. Min Act: -0.1699

Data Index: 1394165 (Python Code)

Max Activating Token Index: 240

Text #11

Max Range: 6.2671. Min Range: -6.2671

Max Act: 6.0076. Min Act: -0.1700

Data Index: 150379 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 6.2671. Min Range: -6.2671

Max Act: 6.0111. Min Act: -0.1690

Data Index: 1544584 (Python Code)

Max Activating Token Index: 856

Text #13

Max Range: 6.2671. Min Range: -6.2671

Max Act: 5.9878. Min Act: -0.1660

Data Index: 24806 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 6.2671. Min Range: -6.2671

Max Act: 5.9878. Min Act: -0.1699

Data Index: 11093 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 6.2671. Min Range: -6.2671

Max Act: 5.9701. Min Act: -0.1700

Data Index: 223953 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 6.2671. Min Range: -6.2671

Max Act: 5.9687. Min Act: -0.1683

Data Index: 1407449 (Python Code)

Max Activating Token Index: 730

Text #17

Max Range: 6.2671. Min Range: -6.2671

Max Act: 5.9352. Min Act: -0.1696

Data Index: 187677 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 6.2671. Min Range: -6.2671

Max Act: 5.9536. Min Act: -0.1700

Data Index: 59709 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 6.2671. Min Range: -6.2671

Max Act: 5.8781. Min Act: -0.1678

Data Index: 460042 (C4 (Web Text))

Max Activating Token Index: 797