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

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

Neuron 1678 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: 3.7633. Min Range: -3.7633

Max Act: 3.7633. Min Act: -0.1700

Data Index: 1014062 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 3.7633. Min Range: -3.7633

Max Act: 3.6694. Min Act: -0.1700

Data Index: 1297693 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 3.7633. Min Range: -3.7633

Max Act: 3.6694. Min Act: -0.1700

Data Index: 909628 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 3.7633. Min Range: -3.7633

Max Act: 3.6381. Min Act: -0.1700

Data Index: 890875 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 3.7633. Min Range: -3.7633

Max Act: 3.6381. Min Act: -0.1700

Data Index: 21101 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 3.7633. Min Range: -3.7633

Max Act: 3.5912. Min Act: -0.1700

Data Index: 539389 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 3.7633. Min Range: -3.7633

Max Act: 3.6381. Min Act: -0.1700

Data Index: 629332 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 3.7633. Min Range: -3.7633

Max Act: 3.6225. Min Act: -0.1700

Data Index: 241619 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 3.7633. Min Range: -3.7633

Max Act: 3.6068. Min Act: -0.1700

Data Index: 232396 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 3.7633. Min Range: -3.7633

Max Act: 3.5912. Min Act: -0.1700

Data Index: 457747 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 3.7633. Min Range: -3.7633

Max Act: 3.5912. Min Act: -0.1700

Data Index: 824640 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 3.7633. Min Range: -3.7633

Max Act: 3.5755. Min Act: -0.1700

Data Index: 877930 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 3.7633. Min Range: -3.7633

Max Act: 3.5598. Min Act: -0.1700

Data Index: 883741 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 3.7633. Min Range: -3.7633

Max Act: 3.5598. Min Act: -0.1700

Data Index: 1025338 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 3.7633. Min Range: -3.7633

Max Act: 3.5598. Min Act: -0.1700

Data Index: 443913 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 3.7633. Min Range: -3.7633

Max Act: 3.5598. Min Act: -0.1700

Data Index: 412188 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 3.7633. Min Range: -3.7633

Max Act: 3.5598. Min Act: -0.1700

Data Index: 725677 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 3.7633. Min Range: -3.7633

Max Act: 3.5442. Min Act: -0.1700

Data Index: 255637 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 3.7633. Min Range: -3.7633

Max Act: 3.5129. Min Act: -0.1700

Data Index: 166338 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 3.7633. Min Range: -3.7633

Max Act: 3.5598. Min Act: -0.1700

Data Index: 540698 (C4 (Web Text))

Max Activating Token Index: 298