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

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

Neuron 187 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.3270. Min Act: -0.1700

Data Index: 263529 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.2958. Min Act: -0.1700

Data Index: 654889 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.1708. Min Act: -0.1700

Data Index: 932920 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.1395. Min Act: -0.1700

Data Index: 53663 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.1395. Min Act: -0.1700

Data Index: 470705 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.1395. Min Act: -0.1700

Data Index: 796943 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.1708. Min Act: -0.1700

Data Index: 1213831 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.2020. Min Act: -0.1700

Data Index: 226426 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.1083. Min Act: -0.1700

Data Index: 375936 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.1083. Min Act: -0.1700

Data Index: 1351697 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.1083. Min Act: -0.1700

Data Index: 533060 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.1395. Min Act: -0.1700

Data Index: 145688 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.0770. Min Act: -0.1700

Data Index: 295655 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.0770. Min Act: -0.1700

Data Index: 1237949 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.0145. Min Act: -0.1700

Data Index: 699061 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.0458. Min Act: -0.1700

Data Index: 1018461 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.0458. Min Act: -0.1700

Data Index: 1061199 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.0458. Min Act: -0.1700

Data Index: 461543 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.0145. Min Act: -0.1700

Data Index: 27979 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 5.3270. Min Range: -5.3270

Max Act: 5.0458. Min Act: -0.1700

Data Index: 224231 (C4 (Web Text))

Max Activating Token Index: 694