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

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

Neuron 1440 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: 5.8627. Min Range: -5.8627

Max Act: 5.8627. Min Act: -0.1700

Data Index: 1252649 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 5.8627. Min Range: -5.8627

Max Act: 5.6908. Min Act: -0.1700

Data Index: 592892 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 5.8627. Min Range: -5.8627

Max Act: 5.6440. Min Act: -0.1700

Data Index: 607424 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 5.8627. Min Range: -5.8627

Max Act: 5.6127. Min Act: -0.1700

Data Index: 1295941 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 5.8627. Min Range: -5.8627

Max Act: 5.6440. Min Act: -0.1700

Data Index: 329722 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 5.8627. Min Range: -5.8627

Max Act: 5.5815. Min Act: -0.1700

Data Index: 32559 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 5.8627. Min Range: -5.8627

Max Act: 5.5815. Min Act: -0.1700

Data Index: 621378 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 5.8627. Min Range: -5.8627

Max Act: 5.5190. Min Act: -0.1700

Data Index: 312018 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 5.8627. Min Range: -5.8627

Max Act: 5.4408. Min Act: -0.1700

Data Index: 958714 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 5.8627. Min Range: -5.8627

Max Act: 5.3315. Min Act: -0.1700

Data Index: 1165865 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 5.8627. Min Range: -5.8627

Max Act: 5.3940. Min Act: -0.1700

Data Index: 677506 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 5.8627. Min Range: -5.8627

Max Act: 5.4096. Min Act: -0.1700

Data Index: 220890 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 5.8627. Min Range: -5.8627

Max Act: 5.4408. Min Act: -0.1700

Data Index: 1269027 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 5.8627. Min Range: -5.8627

Max Act: 5.3471. Min Act: -0.1700

Data Index: 132976 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 5.8627. Min Range: -5.8627

Max Act: 5.3471. Min Act: -0.1700

Data Index: 992511 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 5.8627. Min Range: -5.8627

Max Act: 5.3002. Min Act: -0.1699

Data Index: 920528 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 5.8627. Min Range: -5.8627

Max Act: 5.2221. Min Act: -0.1700

Data Index: 557673 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 5.8627. Min Range: -5.8627

Max Act: 5.2690. Min Act: -0.1700

Data Index: 1303153 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 5.8627. Min Range: -5.8627

Max Act: 5.2690. Min Act: -0.1700

Data Index: 783746 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 5.8627. Min Range: -5.8627

Max Act: 5.2533. Min Act: -0.1700

Data Index: 1338950 (C4 (Web Text))

Max Activating Token Index: 1010