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

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

Neuron 2014 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: 11.0674. Min Range: -11.0674

Max Act: 11.0674. Min Act: -0.1636

Data Index: 785300 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 11.0674. Min Range: -11.0674

Max Act: 10.4009. Min Act: -0.1700

Data Index: 1068348 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 11.0674. Min Range: -11.0674

Max Act: 10.4477. Min Act: 0.2694

Data Index: 1396211 (Python Code)

Max Activating Token Index: 142

Text #3

Max Range: 11.0674. Min Range: -11.0674

Max Act: 10.3948. Min Act: -0.1700

Data Index: 864768 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 11.0674. Min Range: -11.0674

Max Act: 10.3858. Min Act: -0.1548

Data Index: 1336131 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 11.0674. Min Range: -11.0674

Max Act: 10.3035. Min Act: -0.1700

Data Index: 100290 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 11.0674. Min Range: -11.0674

Max Act: 10.2963. Min Act: -0.1678

Data Index: 1428036 (Python Code)

Max Activating Token Index: 548

Text #7

Max Range: 11.0674. Min Range: -11.0674

Max Act: 10.3344. Min Act: -0.1695

Data Index: 1255786 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 11.0674. Min Range: -11.0674

Max Act: 10.2645. Min Act: -0.1529

Data Index: 140828 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 11.0674. Min Range: -11.0674

Max Act: 10.2548. Min Act: -0.1700

Data Index: 1035659 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 11.0674. Min Range: -11.0674

Max Act: 10.1749. Min Act: -0.1699

Data Index: 816194 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 11.0674. Min Range: -11.0674

Max Act: 10.2058. Min Act: -0.1345

Data Index: 1098634 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 11.0674. Min Range: -11.0674

Max Act: 10.0583. Min Act: -0.1609

Data Index: 1413501 (Python Code)

Max Activating Token Index: 628

Text #13

Max Range: 11.0674. Min Range: -11.0674

Max Act: 10.0712. Min Act: -0.1630

Data Index: 1522232 (Python Code)

Max Activating Token Index: 709

Text #14

Max Range: 11.0674. Min Range: -11.0674

Max Act: 10.0232. Min Act: -0.1698

Data Index: 1583111 (Python Code)

Max Activating Token Index: 158

Text #15

Max Range: 11.0674. Min Range: -11.0674

Max Act: 10.0684. Min Act: -0.1535

Data Index: 304117 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 11.0674. Min Range: -11.0674

Max Act: 9.9694. Min Act: -0.1700

Data Index: 968610 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 11.0674. Min Range: -11.0674

Max Act: 9.9686. Min Act: -0.1391

Data Index: 1483349 (Python Code)

Max Activating Token Index: 512

Text #18

Max Range: 11.0674. Min Range: -11.0674

Max Act: 10.0256. Min Act: -0.1675

Data Index: 1476705 (Python Code)

Max Activating Token Index: 484

Text #19

Max Range: 11.0674. Min Range: -11.0674

Max Act: 9.9630. Min Act: -0.1698

Data Index: 1564738 (Python Code)

Max Activating Token Index: 769