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

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

Neuron 1578 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: 3.4852. Min Range: -3.4852

Max Act: 3.4852. Min Act: -0.1700

Data Index: 760185 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.4539. Min Act: -0.1700

Data Index: 523895 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.4696. Min Act: -0.1700

Data Index: 69852 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.4539. Min Act: -0.1700

Data Index: 1010942 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.4539. Min Act: -0.1700

Data Index: 900646 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.4382. Min Act: -0.1700

Data Index: 681221 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.4225. Min Act: -0.1700

Data Index: 1092313 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.3912. Min Act: -0.1700

Data Index: 464759 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.4068. Min Act: -0.1700

Data Index: 102179 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.4068. Min Act: -0.1700

Data Index: 1063139 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.3912. Min Act: -0.1700

Data Index: 550281 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.3912. Min Act: -0.1700

Data Index: 879583 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.3755. Min Act: -0.1700

Data Index: 1319125 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.3912. Min Act: -0.1700

Data Index: 925471 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.3755. Min Act: -0.1700

Data Index: 191164 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.3912. Min Act: -0.1700

Data Index: 293510 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.3912. Min Act: -0.1700

Data Index: 27812 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.3912. Min Act: -0.1700

Data Index: 953254 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.3598. Min Act: -0.1700

Data Index: 799255 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.3598. Min Act: -0.1700

Data Index: 562138 (C4 (Web Text))

Max Activating Token Index: 851