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

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

Neuron 922 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: 3.9755. Min Range: -3.9755

Max Act: 3.9755. Min Act: -0.1700

Data Index: 667025 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 3.9755. Min Range: -3.9755

Max Act: 3.6940. Min Act: -0.1700

Data Index: 1167322 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 3.9755. Min Range: -3.9755

Max Act: 3.6470. Min Act: -0.1700

Data Index: 248848 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 3.9755. Min Range: -3.9755

Max Act: 3.6627. Min Act: -0.1700

Data Index: 753971 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 3.9755. Min Range: -3.9755

Max Act: 3.6313. Min Act: -0.1700

Data Index: 107049 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 3.9755. Min Range: -3.9755

Max Act: 3.6313. Min Act: -0.1700

Data Index: 1345946 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 3.9755. Min Range: -3.9755

Max Act: 3.6313. Min Act: -0.1700

Data Index: 347997 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 3.9755. Min Range: -3.9755

Max Act: 3.6000. Min Act: -0.1700

Data Index: 706533 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 3.9755. Min Range: -3.9755

Max Act: 3.6157. Min Act: -0.1700

Data Index: 842848 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 3.9755. Min Range: -3.9755

Max Act: 3.5687. Min Act: -0.1700

Data Index: 1000297 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 3.9755. Min Range: -3.9755

Max Act: 3.6157. Min Act: -0.1700

Data Index: 819562 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 3.9755. Min Range: -3.9755

Max Act: 3.6470. Min Act: -0.1700

Data Index: 355736 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 3.9755. Min Range: -3.9755

Max Act: 3.5531. Min Act: -0.1700

Data Index: 1288745 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 3.9755. Min Range: -3.9755

Max Act: 3.5844. Min Act: -0.1700

Data Index: 326786 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 3.9755. Min Range: -3.9755

Max Act: 3.5531. Min Act: -0.1700

Data Index: 367019 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 3.9755. Min Range: -3.9755

Max Act: 3.6000. Min Act: -0.1700

Data Index: 363506 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 3.9755. Min Range: -3.9755

Max Act: 3.5687. Min Act: -0.1700

Data Index: 841681 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 3.9755. Min Range: -3.9755

Max Act: 3.5531. Min Act: -0.1700

Data Index: 476668 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 3.9755. Min Range: -3.9755

Max Act: 3.5531. Min Act: -0.1700

Data Index: 662055 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 3.9755. Min Range: -3.9755

Max Act: 3.5374. Min Act: -0.1700

Data Index: 583075 (C4 (Web Text))

Max Activating Token Index: 671