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

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

Neuron 600 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: 3.5773. Min Range: -3.5773

Max Act: 3.5773. Min Act: -0.1700

Data Index: 715024 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.5773. Min Act: -0.1700

Data Index: 434936 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.5460. Min Act: -0.1700

Data Index: 529410 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.5147. Min Act: -0.1700

Data Index: 131000 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.4990. Min Act: -0.1700

Data Index: 1215539 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.4520. Min Act: -0.1700

Data Index: 142352 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.4677. Min Act: -0.1700

Data Index: 1001752 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.4833. Min Act: -0.1700

Data Index: 778655 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.3893. Min Act: -0.1700

Data Index: 533148 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.4206. Min Act: -0.1700

Data Index: 1158577 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.4206. Min Act: -0.1700

Data Index: 442786 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.4206. Min Act: -0.1700

Data Index: 558570 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.4363. Min Act: -0.1700

Data Index: 64716 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.4363. Min Act: -0.1700

Data Index: 570395 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.4206. Min Act: -0.1700

Data Index: 989230 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.3736. Min Act: -0.1700

Data Index: 147345 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.3736. Min Act: -0.1700

Data Index: 964023 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.3736. Min Act: -0.1700

Data Index: 514574 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.3736. Min Act: -0.1700

Data Index: 1251663 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.3893. Min Act: -0.1700

Data Index: 230754 (C4 (Web Text))

Max Activating Token Index: 63