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

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

Neuron 628 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.6663. Min Act: -0.1700

Data Index: 1283139 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.6350. Min Act: -0.1700

Data Index: 948706 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.6194. Min Act: -0.1700

Data Index: 375378 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.6037. Min Act: -0.1700

Data Index: 134337 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5880. Min Act: -0.1700

Data Index: 938048 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5880. Min Act: -0.1700

Data Index: 190154 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5724. Min Act: -0.1700

Data Index: 1159617 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5724. Min Act: -0.1700

Data Index: 1359018 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5880. Min Act: -0.1700

Data Index: 1123225 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5724. Min Act: -0.1700

Data Index: 99509 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5724. Min Act: -0.1700

Data Index: 1240576 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5724. Min Act: -0.1700

Data Index: 659651 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5724. Min Act: -0.1700

Data Index: 1272236 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5567. Min Act: -0.1700

Data Index: 1214793 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5724. Min Act: -0.1700

Data Index: 118936 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5567. Min Act: -0.1700

Data Index: 253218 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5411. Min Act: -0.1700

Data Index: 1183609 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5567. Min Act: -0.1700

Data Index: 877893 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5411. Min Act: -0.1700

Data Index: 892825 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5411. Min Act: -0.1700

Data Index: 1220774 (C4 (Web Text))

Max Activating Token Index: 729