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

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

Neuron 1405 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: 3.6552. Min Range: -3.6552

Max Act: 3.6396. Min Act: -0.1700

Data Index: 1647058 (Python Code)

Max Activating Token Index: 650

Text #1

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.6552. Min Act: -0.1700

Data Index: 1503779 (Python Code)

Max Activating Token Index: 450

Text #2

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.6396. Min Act: -0.1700

Data Index: 1585084 (Python Code)

Max Activating Token Index: 295

Text #3

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.6239. Min Act: -0.1700

Data Index: 819617 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.6082. Min Act: -0.1700

Data Index: 1510616 (Python Code)

Max Activating Token Index: 766

Text #5

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5769. Min Act: -0.1700

Data Index: 1071073 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5769. Min Act: -0.1700

Data Index: 260988 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5769. Min Act: -0.1700

Data Index: 117834 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5926. Min Act: -0.1700

Data Index: 1069949 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5769. Min Act: -0.1700

Data Index: 845848 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5613. Min Act: -0.1700

Data Index: 1579831 (Python Code)

Max Activating Token Index: 541

Text #11

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5926. Min Act: -0.1700

Data Index: 796762 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5613. Min Act: -0.1700

Data Index: 1320370 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.4986. Min Act: -0.1700

Data Index: 1578049 (Python Code)

Max Activating Token Index: 63

Text #14

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5456. Min Act: -0.1700

Data Index: 1417927 (Python Code)

Max Activating Token Index: 489

Text #15

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.4673. Min Act: -0.1700

Data Index: 1406450 (Python Code)

Max Activating Token Index: 635

Text #16

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5143. Min Act: -0.1700

Data Index: 1422009 (Python Code)

Max Activating Token Index: 348

Text #17

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5456. Min Act: -0.1700

Data Index: 354296 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5769. Min Act: -0.1700

Data Index: 998743 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5299. Min Act: -0.1700

Data Index: 195291 (C4 (Web Text))

Max Activating Token Index: 727