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

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

Neuron 820 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: 3.0245. Min Range: -3.0245

Max Act: 3.0245. Min Act: -0.1700

Data Index: 1113025 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 3.0245. Min Range: -3.0245

Max Act: 3.0087. Min Act: -0.1700

Data Index: 516543 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9612. Min Act: -0.1700

Data Index: 74399 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9612. Min Act: -0.1700

Data Index: 59167 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9454. Min Act: -0.1700

Data Index: 230089 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9454. Min Act: -0.1700

Data Index: 1039689 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9295. Min Act: -0.1700

Data Index: 856026 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9295. Min Act: -0.1700

Data Index: 459580 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.8978. Min Act: -0.1700

Data Index: 307730 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.8978. Min Act: -0.1700

Data Index: 328309 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.8820. Min Act: -0.1700

Data Index: 1048967 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.8978. Min Act: -0.1700

Data Index: 172218 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.8661. Min Act: -0.1700

Data Index: 781844 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.8820. Min Act: -0.1700

Data Index: 1167203 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.8820. Min Act: -0.1700

Data Index: 1076427 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.8661. Min Act: -0.1700

Data Index: 1315615 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.8820. Min Act: -0.1700

Data Index: 687895 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.8661. Min Act: -0.1700

Data Index: 732646 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.8661. Min Act: -0.1700

Data Index: 53278 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.8502. Min Act: -0.1700

Data Index: 357306 (C4 (Web Text))

Max Activating Token Index: 775