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

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

Neuron 566 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.8402. Min Act: -0.1699

Data Index: 358814 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.8246. Min Act: -0.1700

Data Index: 47213 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.7620. Min Act: -0.1700

Data Index: 771791 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.7777. Min Act: -0.1700

Data Index: 1160503 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.7464. Min Act: -0.1699

Data Index: 1251659 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.7464. Min Act: -0.1700

Data Index: 929012 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.6994. Min Act: -0.1699

Data Index: 1256644 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.7307. Min Act: -0.1700

Data Index: 163781 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.7151. Min Act: -0.1699

Data Index: 856762 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.7151. Min Act: -0.1700

Data Index: 1043901 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.6994. Min Act: -0.1699

Data Index: 62302 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.7151. Min Act: -0.1700

Data Index: 12658 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.6838. Min Act: -0.1700

Data Index: 1053097 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.6838. Min Act: -0.1699

Data Index: 514072 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.6838. Min Act: -0.1700

Data Index: 993828 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.6525. Min Act: -0.1700

Data Index: 1297837 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.6525. Min Act: -0.1700

Data Index: 1101470 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.7151. Min Act: -0.1700

Data Index: 596861 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.6525. Min Act: -0.1700

Data Index: 963221 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 3.8402. Min Range: -3.8402

Max Act: 3.6681. Min Act: -0.1699

Data Index: 253505 (C4 (Web Text))

Max Activating Token Index: 384