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

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

Neuron 1123 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: 9.0491. Min Range: -9.0491

Max Act: 9.0491. Min Act: -0.1699

Data Index: 620013 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 9.0491. Min Range: -9.0491

Max Act: 8.8616. Min Act: -0.1700

Data Index: 232909 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 9.0491. Min Range: -9.0491

Max Act: 8.9866. Min Act: -0.1699

Data Index: 60315 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 9.0491. Min Range: -9.0491

Max Act: 8.7991. Min Act: -0.1673

Data Index: 1009880 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 9.0491. Min Range: -9.0491

Max Act: 8.7366. Min Act: -0.1700

Data Index: 991316 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 9.0491. Min Range: -9.0491

Max Act: 8.7991. Min Act: -0.1687

Data Index: 1339380 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 9.0491. Min Range: -9.0491

Max Act: 8.7366. Min Act: -0.1699

Data Index: 1170582 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 9.0491. Min Range: -9.0491

Max Act: 8.7366. Min Act: -0.1699

Data Index: 168415 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 9.0491. Min Range: -9.0491

Max Act: 8.7366. Min Act: -0.1700

Data Index: 907852 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 9.0491. Min Range: -9.0491

Max Act: 8.6741. Min Act: -0.1700

Data Index: 428133 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 9.0491. Min Range: -9.0491

Max Act: 8.6741. Min Act: -0.1700

Data Index: 512918 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 9.0491. Min Range: -9.0491

Max Act: 8.6741. Min Act: -0.1700

Data Index: 1024240 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 9.0491. Min Range: -9.0491

Max Act: 8.6116. Min Act: -0.1700

Data Index: 1151498 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 9.0491. Min Range: -9.0491

Max Act: 8.6116. Min Act: -0.1700

Data Index: 186712 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 9.0491. Min Range: -9.0491

Max Act: 8.6741. Min Act: -0.1615

Data Index: 669349 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 9.0491. Min Range: -9.0491

Max Act: 8.4866. Min Act: -0.1700

Data Index: 1153696 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 9.0491. Min Range: -9.0491

Max Act: 8.6116. Min Act: -0.1700

Data Index: 1132227 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 9.0491. Min Range: -9.0491

Max Act: 8.6741. Min Act: -0.1700

Data Index: 585207 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 9.0491. Min Range: -9.0491

Max Act: 8.4866. Min Act: -0.1699

Data Index: 231922 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 9.0491. Min Range: -9.0491

Max Act: 8.6116. Min Act: -0.1700

Data Index: 911060 (C4 (Web Text))

Max Activating Token Index: 276