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

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

Neuron 1527 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: 3.1627. Min Range: -3.1627

Max Act: 3.1627. Min Act: -0.1700

Data Index: 607709 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.1470. Min Act: -0.1700

Data Index: 269251 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.1312. Min Act: -0.1700

Data Index: 1131425 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0839. Min Act: -0.1700

Data Index: 445578 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0839. Min Act: -0.1700

Data Index: 1009614 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0681. Min Act: -0.1700

Data Index: 1238685 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0681. Min Act: -0.1700

Data Index: 237829 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0681. Min Act: -0.1700

Data Index: 1248855 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0524. Min Act: -0.1700

Data Index: 245445 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0524. Min Act: -0.1700

Data Index: 1114236 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0524. Min Act: -0.1700

Data Index: 87214 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0524. Min Act: -0.1700

Data Index: 125416 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0524. Min Act: -0.1700

Data Index: 570951 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0366. Min Act: -0.1700

Data Index: 865705 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0208. Min Act: -0.1700

Data Index: 86783 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0050. Min Act: -0.1700

Data Index: 175382 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0208. Min Act: -0.1700

Data Index: 166078 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0366. Min Act: -0.1700

Data Index: 12873 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0208. Min Act: -0.1700

Data Index: 448719 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0208. Min Act: -0.1700

Data Index: 148245 (C4 (Web Text))

Max Activating Token Index: 390