Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1017 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.4521. Min Act: -0.1700

Data Index: 1319166 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.3580. Min Act: -0.1700

Data Index: 871858 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.3109. Min Act: -0.1700

Data Index: 90349 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.2481. Min Act: -0.1700

Data Index: 31414 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.2166. Min Act: -0.1700

Data Index: 1193470 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.2009. Min Act: -0.1700

Data Index: 41817 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.1537. Min Act: -0.1700

Data Index: 76213 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.1537. Min Act: -0.1700

Data Index: 729135 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.1379. Min Act: -0.1700

Data Index: 75110 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.1379. Min Act: -0.1700

Data Index: 668148 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.1222. Min Act: -0.1700

Data Index: 1019331 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.1222. Min Act: -0.1700

Data Index: 482842 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.0749. Min Act: -0.1700

Data Index: 309578 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.0906. Min Act: -0.1700

Data Index: 364321 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.0433. Min Act: -0.1700

Data Index: 125100 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.0591. Min Act: -0.1700

Data Index: 100352 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.0433. Min Act: -0.1700

Data Index: 1627646 (Python Code)

Max Activating Token Index: 657

Text #17

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.0591. Min Act: -0.1700

Data Index: 1023371 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.0591. Min Act: -0.1700

Data Index: 1162454 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.0591. Min Act: -0.1700

Data Index: 722608 (C4 (Web Text))

Max Activating Token Index: 385