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

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

Neuron 524 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.7975. Min Act: -0.1700

Data Index: 554815 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.7037. Min Act: -0.1700

Data Index: 80922 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.5787. Min Act: -0.1698

Data Index: 1288679 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.5162. Min Act: -0.1700

Data Index: 1094829 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.5475. Min Act: -0.1700

Data Index: 86075 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.4850. Min Act: -0.1700

Data Index: 386457 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.4537. Min Act: -0.1700

Data Index: 677105 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.4537. Min Act: -0.1700

Data Index: 1027145 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.4225. Min Act: -0.1700

Data Index: 763242 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.4225. Min Act: -0.1700

Data Index: 747481 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.3600. Min Act: -0.1700

Data Index: 664783 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.2975. Min Act: -0.1700

Data Index: 771910 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.1725. Min Act: -0.1700

Data Index: 11443 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.2037. Min Act: -0.1700

Data Index: 697613 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.1725. Min Act: -0.1700

Data Index: 768561 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.2037. Min Act: -0.1700

Data Index: 1313444 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.2037. Min Act: -0.1700

Data Index: 352112 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.1725. Min Act: -0.1700

Data Index: 982037 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.1100. Min Act: -0.1700

Data Index: 1138729 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 7.7975. Min Range: -7.7975

Max Act: 7.1412. Min Act: -0.1700

Data Index: 953474 (C4 (Web Text))

Max Activating Token Index: 835