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

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

Neuron 817 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: 3.4738. Min Range: -3.4738

Max Act: 3.4738. Min Act: -0.1700

Data Index: 1287127 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.3954. Min Act: -0.1700

Data Index: 709721 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.3326. Min Act: -0.1700

Data Index: 159026 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.3012. Min Act: -0.1700

Data Index: 1026197 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.2541. Min Act: -0.1700

Data Index: 974871 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.2855. Min Act: -0.1700

Data Index: 1253754 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.2384. Min Act: -0.1700

Data Index: 1022635 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.1912. Min Act: -0.1700

Data Index: 1272248 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.2384. Min Act: -0.1700

Data Index: 355080 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.1912. Min Act: -0.1700

Data Index: 89704 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.2226. Min Act: -0.1700

Data Index: 68923 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.1754. Min Act: -0.1700

Data Index: 1091197 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.2226. Min Act: -0.1700

Data Index: 818773 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.2226. Min Act: -0.1700

Data Index: 667612 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.1754. Min Act: -0.1700

Data Index: 1333972 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.1597. Min Act: -0.1700

Data Index: 1316489 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.1754. Min Act: -0.1700

Data Index: 938881 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.1912. Min Act: -0.1700

Data Index: 604914 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.1597. Min Act: -0.1700

Data Index: 818954 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.1439. Min Act: -0.1700

Data Index: 1209719 (C4 (Web Text))

Max Activating Token Index: 330