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

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

Neuron 1403 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: 5.0523. Min Range: -5.0523

Max Act: 5.0523. Min Act: -0.1700

Data Index: 283 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.9898. Min Act: -0.1700

Data Index: 1024382 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.9898. Min Act: -0.1700

Data Index: 822176 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.8648. Min Act: -0.1700

Data Index: 1024857 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.7398. Min Act: -0.1700

Data Index: 1247476 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.7711. Min Act: -0.1700

Data Index: 1159779 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.8023. Min Act: -0.1700

Data Index: 1196587 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.8023. Min Act: -0.1700

Data Index: 407881 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.7711. Min Act: -0.1662

Data Index: 152501 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.7086. Min Act: -0.1700

Data Index: 1100416 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.6773. Min Act: -0.1700

Data Index: 430873 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.6773. Min Act: -0.1700

Data Index: 996730 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.6148. Min Act: -0.1676

Data Index: 871198 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.6773. Min Act: -0.1700

Data Index: 669350 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.6148. Min Act: -0.1700

Data Index: 453827 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.6148. Min Act: -0.1700

Data Index: 1047322 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.6148. Min Act: -0.1700

Data Index: 109073 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.6148. Min Act: -0.1700

Data Index: 1157046 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.6148. Min Act: -0.1700

Data Index: 166089 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.5836. Min Act: -0.1700

Data Index: 5548 (C4 (Web Text))

Max Activating Token Index: 74