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

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

Neuron 1204 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: 3.9624. Min Range: -3.9624

Max Act: 3.9624. Min Act: -0.1700

Data Index: 381174 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 3.9624. Min Range: -3.9624

Max Act: 3.8842. Min Act: -0.1700

Data Index: 471088 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 3.9624. Min Range: -3.9624

Max Act: 3.8216. Min Act: -0.1700

Data Index: 984233 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 3.9624. Min Range: -3.9624

Max Act: 3.8216. Min Act: -0.1700

Data Index: 728209 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 3.9624. Min Range: -3.9624

Max Act: 3.8060. Min Act: -0.1700

Data Index: 1174427 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 3.9624. Min Range: -3.9624

Max Act: 3.7903. Min Act: -0.1700

Data Index: 1173999 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 3.9624. Min Range: -3.9624

Max Act: 3.7747. Min Act: -0.1700

Data Index: 1354225 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 3.9624. Min Range: -3.9624

Max Act: 3.7747. Min Act: -0.1700

Data Index: 430809 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 3.9624. Min Range: -3.9624

Max Act: 3.7903. Min Act: -0.1700

Data Index: 234392 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 3.9624. Min Range: -3.9624

Max Act: 3.7903. Min Act: -0.1700

Data Index: 934295 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 3.9624. Min Range: -3.9624

Max Act: 3.7747. Min Act: -0.1700

Data Index: 1317841 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 3.9624. Min Range: -3.9624

Max Act: 3.7747. Min Act: -0.1700

Data Index: 1246636 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 3.9624. Min Range: -3.9624

Max Act: 3.7747. Min Act: -0.1700

Data Index: 1221788 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 3.9624. Min Range: -3.9624

Max Act: 3.7747. Min Act: -0.1700

Data Index: 801059 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 3.9624. Min Range: -3.9624

Max Act: 3.7903. Min Act: -0.1700

Data Index: 788390 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 3.9624. Min Range: -3.9624

Max Act: 3.7903. Min Act: -0.1700

Data Index: 519111 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 3.9624. Min Range: -3.9624

Max Act: 3.7591. Min Act: -0.1700

Data Index: 351202 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 3.9624. Min Range: -3.9624

Max Act: 3.7747. Min Act: -0.1700

Data Index: 426807 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 3.9624. Min Range: -3.9624

Max Act: 3.7591. Min Act: -0.1700

Data Index: 964538 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 3.9624. Min Range: -3.9624

Max Act: 3.7591. Min Act: -0.1700

Data Index: 114793 (C4 (Web Text))

Max Activating Token Index: 807