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

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

Neuron 1765 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0021. Min Range: -3.0021

Max Act: 3.0021. Min Act: -0.1700

Data Index: 998748 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.9230. Min Act: -0.1700

Data Index: 489065 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.8595. Min Act: -0.1700

Data Index: 903364 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.8277. Min Act: -0.1700

Data Index: 839571 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.8595. Min Act: -0.1700

Data Index: 1060316 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.8436. Min Act: -0.1700

Data Index: 400993 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.8595. Min Act: -0.1700

Data Index: 846009 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.8913. Min Act: -0.1700

Data Index: 340376 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.8277. Min Act: -0.1700

Data Index: 518962 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.8436. Min Act: -0.1700

Data Index: 408710 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.8277. Min Act: -0.1700

Data Index: 1125407 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.8277. Min Act: -0.1700

Data Index: 216450 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.8436. Min Act: -0.1700

Data Index: 850965 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.7959. Min Act: -0.1700

Data Index: 789731 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.8118. Min Act: -0.1700

Data Index: 1131652 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.7959. Min Act: -0.1700

Data Index: 114864 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.7959. Min Act: -0.1700

Data Index: 944076 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.8436. Min Act: -0.1700

Data Index: 398215 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.7959. Min Act: -0.1700

Data Index: 32612 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.7799. Min Act: -0.1700

Data Index: 121416 (C4 (Web Text))

Max Activating Token Index: 918