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

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

Neuron 1057 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: 3.9032. Min Range: -3.9032

Max Act: 3.9032. Min Act: -0.1700

Data Index: 784574 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 3.9032. Min Range: -3.9032

Max Act: 3.8407. Min Act: -0.1700

Data Index: 1235689 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 3.9032. Min Range: -3.9032

Max Act: 3.8407. Min Act: -0.1700

Data Index: 1273830 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 3.9032. Min Range: -3.9032

Max Act: 3.8719. Min Act: -0.1700

Data Index: 686834 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 3.9032. Min Range: -3.9032

Max Act: 3.8094. Min Act: -0.1700

Data Index: 1217506 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 3.9032. Min Range: -3.9032

Max Act: 3.7781. Min Act: -0.1700

Data Index: 1080964 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 3.9032. Min Range: -3.9032

Max Act: 3.7468. Min Act: -0.1700

Data Index: 1139357 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 3.9032. Min Range: -3.9032

Max Act: 3.8094. Min Act: -0.1700

Data Index: 901318 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 3.9032. Min Range: -3.9032

Max Act: 3.8094. Min Act: -0.1700

Data Index: 3655 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 3.9032. Min Range: -3.9032

Max Act: 3.7468. Min Act: -0.1700

Data Index: 684355 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 3.9032. Min Range: -3.9032

Max Act: 3.6529. Min Act: -0.1700

Data Index: 237502 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 3.9032. Min Range: -3.9032

Max Act: 3.6216. Min Act: -0.1700

Data Index: 895004 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 3.9032. Min Range: -3.9032

Max Act: 3.6216. Min Act: -0.1700

Data Index: 259661 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 3.9032. Min Range: -3.9032

Max Act: 3.6216. Min Act: -0.1700

Data Index: 521737 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 3.9032. Min Range: -3.9032

Max Act: 3.6529. Min Act: -0.1700

Data Index: 264867 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 3.9032. Min Range: -3.9032

Max Act: 3.6216. Min Act: -0.1700

Data Index: 576733 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 3.9032. Min Range: -3.9032

Max Act: 3.5903. Min Act: -0.1700

Data Index: 415851 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 3.9032. Min Range: -3.9032

Max Act: 3.5590. Min Act: -0.1700

Data Index: 151891 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 3.9032. Min Range: -3.9032

Max Act: 3.5903. Min Act: -0.1700

Data Index: 172739 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 3.9032. Min Range: -3.9032

Max Act: 3.5590. Min Act: -0.1700

Data Index: 352338 (C4 (Web Text))

Max Activating Token Index: 795