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

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

Neuron 1252 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.7584. Min Act: -0.1700

Data Index: 364449 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.6958. Min Act: -0.1700

Data Index: 866962 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.6958. Min Act: -0.1700

Data Index: 991874 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.6958. Min Act: -0.1700

Data Index: 448611 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.6958. Min Act: -0.1700

Data Index: 1260345 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.6645. Min Act: -0.1700

Data Index: 313509 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.6645. Min Act: -0.1700

Data Index: 561682 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.6645. Min Act: -0.1700

Data Index: 999966 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.6645. Min Act: -0.1700

Data Index: 433374 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.6645. Min Act: -0.1700

Data Index: 874176 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.6332. Min Act: -0.1700

Data Index: 1232175 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.6332. Min Act: -0.1700

Data Index: 667658 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.6645. Min Act: -0.1700

Data Index: 1217847 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.6645. Min Act: -0.1700

Data Index: 896608 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.6019. Min Act: -0.1700

Data Index: 322884 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.6332. Min Act: -0.1700

Data Index: 1358282 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.6019. Min Act: -0.1700

Data Index: 299896 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.6019. Min Act: -0.1700

Data Index: 1250604 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.6019. Min Act: -0.1700

Data Index: 1144401 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 3.7584. Min Range: -3.7584

Max Act: 3.6019. Min Act: -0.1700

Data Index: 61545 (C4 (Web Text))

Max Activating Token Index: 95