Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1737 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.6462. Min Act: -0.1700

Data Index: 715166 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.5679. Min Act: -0.1700

Data Index: 960612 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.5053. Min Act: -0.1700

Data Index: 188756 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.4896. Min Act: -0.1700

Data Index: 918835 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.4896. Min Act: -0.1700

Data Index: 965767 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.4739. Min Act: -0.1700

Data Index: 1308051 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.4739. Min Act: -0.1700

Data Index: 1261355 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.4583. Min Act: -0.1700

Data Index: 913820 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.4583. Min Act: -0.1700

Data Index: 1208792 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.4269. Min Act: -0.1700

Data Index: 1078384 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.4112. Min Act: -0.1700

Data Index: 3178 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.4269. Min Act: -0.1700

Data Index: 796148 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.3798. Min Act: -0.1700

Data Index: 932860 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.3798. Min Act: -0.1700

Data Index: 749338 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.3642. Min Act: -0.1700

Data Index: 1090563 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.3485. Min Act: -0.1700

Data Index: 1138055 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.3328. Min Act: -0.1700

Data Index: 733854 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.3642. Min Act: -0.1700

Data Index: 308842 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.3642. Min Act: -0.1700

Data Index: 551705 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.3485. Min Act: -0.1700

Data Index: 1156236 (C4 (Web Text))

Max Activating Token Index: 213