Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1770 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.9695. Min Act: -0.1700

Data Index: 176357 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.9539. Min Act: -0.1699

Data Index: 745363 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.9539. Min Act: -0.1700

Data Index: 277781 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.9070. Min Act: -0.1700

Data Index: 811889 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.9070. Min Act: -0.1699

Data Index: 1115623 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.8757. Min Act: -0.1700

Data Index: 879727 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.8601. Min Act: -0.1700

Data Index: 425923 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.7975. Min Act: -0.1700

Data Index: 121451 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.8444. Min Act: -0.1700

Data Index: 341015 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.8288. Min Act: -0.1700

Data Index: 1123240 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.8288. Min Act: -0.1700

Data Index: 748334 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.8288. Min Act: -0.1700

Data Index: 369056 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.8288. Min Act: -0.1700

Data Index: 137880 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.7662. Min Act: -0.1700

Data Index: 619146 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.7193. Min Act: -0.1700

Data Index: 1003965 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.7975. Min Act: -0.1700

Data Index: 1017187 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.7819. Min Act: -0.1700

Data Index: 1006311 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.7975. Min Act: -0.1700

Data Index: 610024 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.8288. Min Act: -0.1700

Data Index: 382777 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 3.9695. Min Range: -3.9695

Max Act: 3.7662. Min Act: -0.1700

Data Index: 1121357 (C4 (Web Text))

Max Activating Token Index: 107