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

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

Neuron 422 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: 3.8518. Min Range: -3.8518

Max Act: 3.8518. Min Act: -0.1700

Data Index: 44682 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 3.8518. Min Range: -3.8518

Max Act: 3.7266. Min Act: -0.1700

Data Index: 658541 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 3.8518. Min Range: -3.8518

Max Act: 3.7266. Min Act: -0.1700

Data Index: 104374 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 3.8518. Min Range: -3.8518

Max Act: 3.7579. Min Act: -0.1700

Data Index: 917768 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 3.8518. Min Range: -3.8518

Max Act: 3.6640. Min Act: -0.1700

Data Index: 1247915 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 3.8518. Min Range: -3.8518

Max Act: 3.7266. Min Act: -0.1700

Data Index: 1114454 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 3.8518. Min Range: -3.8518

Max Act: 3.6953. Min Act: -0.1700

Data Index: 289489 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 3.8518. Min Range: -3.8518

Max Act: 3.6640. Min Act: -0.1700

Data Index: 1329463 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 3.8518. Min Range: -3.8518

Max Act: 3.6640. Min Act: -0.1700

Data Index: 686196 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.8518. Min Range: -3.8518

Max Act: 3.6953. Min Act: -0.1700

Data Index: 760556 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 3.8518. Min Range: -3.8518

Max Act: 3.6327. Min Act: -0.1700

Data Index: 1291708 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 3.8518. Min Range: -3.8518

Max Act: 3.6640. Min Act: -0.1700

Data Index: 525089 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 3.8518. Min Range: -3.8518

Max Act: 3.6640. Min Act: -0.1700

Data Index: 723729 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 3.8518. Min Range: -3.8518

Max Act: 3.6327. Min Act: -0.1700

Data Index: 12663 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 3.8518. Min Range: -3.8518

Max Act: 3.5701. Min Act: -0.1700

Data Index: 490923 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 3.8518. Min Range: -3.8518

Max Act: 3.6014. Min Act: -0.1700

Data Index: 797985 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 3.8518. Min Range: -3.8518

Max Act: 3.6327. Min Act: -0.1700

Data Index: 809854 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 3.8518. Min Range: -3.8518

Max Act: 3.6014. Min Act: -0.1700

Data Index: 1212663 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 3.8518. Min Range: -3.8518

Max Act: 3.6327. Min Act: -0.1700

Data Index: 685245 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 3.8518. Min Range: -3.8518

Max Act: 3.5388. Min Act: -0.1700

Data Index: 870375 (C4 (Web Text))

Max Activating Token Index: 866