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

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

Neuron 1867 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.8796. Min Act: -0.1700

Data Index: 64987 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.8483. Min Act: -0.1700

Data Index: 1292771 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.7857. Min Act: -0.1700

Data Index: 993304 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.6293. Min Act: -0.1700

Data Index: 1076547 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.6293. Min Act: -0.1700

Data Index: 1172197 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.5666. Min Act: -0.1700

Data Index: 21559 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.5040. Min Act: -0.1700

Data Index: 1043580 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.5040. Min Act: -0.1700

Data Index: 1066544 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.5040. Min Act: -0.1700

Data Index: 858597 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.5353. Min Act: -0.1700

Data Index: 421936 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.5040. Min Act: -0.1700

Data Index: 1003230 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.4413. Min Act: -0.1700

Data Index: 471678 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.4413. Min Act: -0.1700

Data Index: 1116745 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.4413. Min Act: -0.1700

Data Index: 856994 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.4726. Min Act: -0.1700

Data Index: 509207 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.4099. Min Act: -0.1700

Data Index: 88476 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.4099. Min Act: -0.1700

Data Index: 1060672 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.4099. Min Act: -0.1700

Data Index: 891759 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.4099. Min Act: -0.1700

Data Index: 807449 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.4099. Min Act: -0.1700

Data Index: 599126 (C4 (Web Text))

Max Activating Token Index: 816