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

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

Neuron 835 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1554. Min Range: -3.1554

Max Act: 3.1554. Min Act: -0.1700

Data Index: 595707 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 3.1554. Min Range: -3.1554

Max Act: 3.1239. Min Act: -0.1700

Data Index: 1250130 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 3.1554. Min Range: -3.1554

Max Act: 3.1081. Min Act: -0.1700

Data Index: 1246661 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 3.1554. Min Range: -3.1554

Max Act: 3.1239. Min Act: -0.1700

Data Index: 116600 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 3.1554. Min Range: -3.1554

Max Act: 3.1081. Min Act: -0.1700

Data Index: 907211 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 3.1554. Min Range: -3.1554

Max Act: 3.1081. Min Act: -0.1700

Data Index: 669571 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 3.1554. Min Range: -3.1554

Max Act: 3.1081. Min Act: -0.1700

Data Index: 636180 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 3.1554. Min Range: -3.1554

Max Act: 3.0924. Min Act: -0.1700

Data Index: 582177 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 3.1554. Min Range: -3.1554

Max Act: 3.0608. Min Act: -0.1700

Data Index: 437920 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 3.1554. Min Range: -3.1554

Max Act: 3.0292. Min Act: -0.1700

Data Index: 484975 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 3.1554. Min Range: -3.1554

Max Act: 3.0292. Min Act: -0.1700

Data Index: 166376 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 3.1554. Min Range: -3.1554

Max Act: 3.0134. Min Act: -0.1700

Data Index: 241309 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 3.1554. Min Range: -3.1554

Max Act: 3.0292. Min Act: -0.1700

Data Index: 1190961 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 3.1554. Min Range: -3.1554

Max Act: 2.9976. Min Act: -0.1700

Data Index: 1533132 (Python Code)

Max Activating Token Index: 661

Text #14

Max Range: 3.1554. Min Range: -3.1554

Max Act: 2.9976. Min Act: -0.1700

Data Index: 514597 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 3.1554. Min Range: -3.1554

Max Act: 2.9976. Min Act: -0.1700

Data Index: 1068371 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 3.1554. Min Range: -3.1554

Max Act: 2.9818. Min Act: -0.1700

Data Index: 1040470 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 3.1554. Min Range: -3.1554

Max Act: 2.9660. Min Act: -0.1700

Data Index: 10590 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 3.1554. Min Range: -3.1554

Max Act: 2.9660. Min Act: -0.1700

Data Index: 1192191 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 3.1554. Min Range: -3.1554

Max Act: 2.9660. Min Act: -0.1700

Data Index: 760165 (C4 (Web Text))

Max Activating Token Index: 865