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

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

Neuron 1202 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: 4.1819. Min Range: -4.1819

Max Act: 4.1819. Min Act: -0.1700

Data Index: 1170582 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 4.1819. Min Range: -4.1819

Max Act: 4.0569. Min Act: -0.1700

Data Index: 547137 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9318. Min Act: -0.1700

Data Index: 474330 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9944. Min Act: -0.1700

Data Index: 825982 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9944. Min Act: -0.1700

Data Index: 983424 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9944. Min Act: -0.1700

Data Index: 103207 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9944. Min Act: -0.1700

Data Index: 652414 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9318. Min Act: -0.1700

Data Index: 653708 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9944. Min Act: -0.1700

Data Index: 1065515 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.8380. Min Act: -0.1700

Data Index: 915312 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9006. Min Act: -0.1700

Data Index: 682874 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9318. Min Act: -0.1700

Data Index: 498535 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9006. Min Act: -0.1700

Data Index: 329664 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9006. Min Act: -0.1700

Data Index: 943424 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9006. Min Act: -0.1700

Data Index: 323329 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9318. Min Act: -0.1700

Data Index: 883130 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9318. Min Act: -0.1700

Data Index: 1109684 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.8380. Min Act: -0.1700

Data Index: 375571 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.8693. Min Act: -0.1700

Data Index: 391877 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9006. Min Act: -0.1700

Data Index: 949818 (C4 (Web Text))

Max Activating Token Index: 793