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

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

Neuron 344 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.3993. Min Act: -0.1700

Data Index: 710723 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.3993. Min Act: -0.1700

Data Index: 601585 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.3993. Min Act: -0.1700

Data Index: 309834 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.3681. Min Act: -0.1700

Data Index: 573368 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.2431. Min Act: -0.1700

Data Index: 682714 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.1181. Min Act: -0.1700

Data Index: 1290152 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.2743. Min Act: -0.1700

Data Index: 653389 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.1806. Min Act: -0.1700

Data Index: 1060466 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.2118. Min Act: -0.1700

Data Index: 735187 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.1806. Min Act: -0.1700

Data Index: 1109924 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.1493. Min Act: -0.1700

Data Index: 454366 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.1181. Min Act: -0.1700

Data Index: 138328 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.0868. Min Act: -0.1700

Data Index: 994454 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.2431. Min Act: -0.1700

Data Index: 804833 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.1806. Min Act: -0.1700

Data Index: 844533 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.0556. Min Act: -0.1700

Data Index: 1164264 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.0868. Min Act: -0.1700

Data Index: 484821 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.0556. Min Act: -0.1700

Data Index: 706097 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.0243. Min Act: -0.1700

Data Index: 943888 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 5.3993. Min Range: -5.3993

Max Act: 5.0243. Min Act: -0.1700

Data Index: 1218697 (C4 (Web Text))

Max Activating Token Index: 538