Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1072 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 8.0261. Min Range: -8.0261

Max Act: 8.0261. Min Act: -0.1671

Data Index: 1327531 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 8.0261. Min Range: -8.0261

Max Act: 8.0261. Min Act: -0.1700

Data Index: 1168282 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 8.0261. Min Range: -8.0261

Max Act: 7.9636. Min Act: -0.1700

Data Index: 129892 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 8.0261. Min Range: -8.0261

Max Act: 7.9636. Min Act: -0.1700

Data Index: 963826 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 8.0261. Min Range: -8.0261

Max Act: 7.8386. Min Act: -0.1700

Data Index: 369616 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 8.0261. Min Range: -8.0261

Max Act: 7.9011. Min Act: -0.1700

Data Index: 598576 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 8.0261. Min Range: -8.0261

Max Act: 7.8386. Min Act: -0.1700

Data Index: 736992 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 8.0261. Min Range: -8.0261

Max Act: 7.8386. Min Act: -0.1700

Data Index: 593035 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 8.0261. Min Range: -8.0261

Max Act: 7.7136. Min Act: -0.1700

Data Index: 1125322 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 8.0261. Min Range: -8.0261

Max Act: 7.7761. Min Act: -0.1700

Data Index: 962425 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 8.0261. Min Range: -8.0261

Max Act: 7.7136. Min Act: -0.1295

Data Index: 719797 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 8.0261. Min Range: -8.0261

Max Act: 7.6511. Min Act: -0.1700

Data Index: 1054255 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 8.0261. Min Range: -8.0261

Max Act: 7.7761. Min Act: -0.1700

Data Index: 1218953 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 8.0261. Min Range: -8.0261

Max Act: 7.6511. Min Act: -0.1700

Data Index: 1252083 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 8.0261. Min Range: -8.0261

Max Act: 7.6511. Min Act: -0.1700

Data Index: 1026667 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 8.0261. Min Range: -8.0261

Max Act: 7.6511. Min Act: -0.1700

Data Index: 500872 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 8.0261. Min Range: -8.0261

Max Act: 7.6511. Min Act: -0.1700

Data Index: 1255585 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 8.0261. Min Range: -8.0261

Max Act: 7.5261. Min Act: -0.1700

Data Index: 183754 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 8.0261. Min Range: -8.0261

Max Act: 7.4636. Min Act: -0.1700

Data Index: 158577 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 8.0261. Min Range: -8.0261

Max Act: 7.5261. Min Act: -0.1700

Data Index: 1082776 (C4 (Web Text))

Max Activating Token Index: 343