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

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

Neuron 1199 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.6415. Min Act: -0.1700

Data Index: 542492 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.6258. Min Act: -0.1700

Data Index: 251419 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5945. Min Act: -0.1700

Data Index: 760400 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.6102. Min Act: -0.1700

Data Index: 680542 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.6102. Min Act: -0.1700

Data Index: 1202225 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5945. Min Act: -0.1700

Data Index: 935879 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5789. Min Act: -0.1700

Data Index: 531158 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5789. Min Act: -0.1700

Data Index: 942106 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5789. Min Act: -0.1700

Data Index: 311277 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5789. Min Act: -0.1700

Data Index: 718261 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5632. Min Act: -0.1700

Data Index: 542245 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5632. Min Act: -0.1700

Data Index: 1283616 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5632. Min Act: -0.1700

Data Index: 52215 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5475. Min Act: -0.1700

Data Index: 172016 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5789. Min Act: -0.1700

Data Index: 527846 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5475. Min Act: -0.1700

Data Index: 253490 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5475. Min Act: -0.1700

Data Index: 339017 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5475. Min Act: -0.1700

Data Index: 903577 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5475. Min Act: -0.1700

Data Index: 43842 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5319. Min Act: -0.1700

Data Index: 782788 (C4 (Web Text))

Max Activating Token Index: 192