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

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

Neuron 1175 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: 3.2648. Min Range: -3.2648

Max Act: 3.2648. Min Act: -0.1700

Data Index: 828959 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 3.2648. Min Range: -3.2648

Max Act: 3.2177. Min Act: -0.1700

Data Index: 237819 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 3.2648. Min Range: -3.2648

Max Act: 3.2177. Min Act: -0.1700

Data Index: 841891 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 3.2648. Min Range: -3.2648

Max Act: 3.1862. Min Act: -0.1700

Data Index: 1339299 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 3.2648. Min Range: -3.2648

Max Act: 3.1862. Min Act: -0.1700

Data Index: 698082 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 3.2648. Min Range: -3.2648

Max Act: 3.2020. Min Act: -0.1700

Data Index: 562786 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 3.2648. Min Range: -3.2648

Max Act: 3.1705. Min Act: -0.1700

Data Index: 773826 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 3.2648. Min Range: -3.2648

Max Act: 3.1705. Min Act: -0.1700

Data Index: 194659 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 3.2648. Min Range: -3.2648

Max Act: 3.1547. Min Act: -0.1700

Data Index: 933963 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 3.2648. Min Range: -3.2648

Max Act: 3.1547. Min Act: -0.1700

Data Index: 1234036 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 3.2648. Min Range: -3.2648

Max Act: 3.1547. Min Act: -0.1700

Data Index: 416730 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 3.2648. Min Range: -3.2648

Max Act: 3.1390. Min Act: -0.1700

Data Index: 554052 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 3.2648. Min Range: -3.2648

Max Act: 3.1547. Min Act: -0.1700

Data Index: 625639 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 3.2648. Min Range: -3.2648

Max Act: 3.1232. Min Act: -0.1700

Data Index: 1343142 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 3.2648. Min Range: -3.2648

Max Act: 3.1232. Min Act: -0.1700

Data Index: 406592 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 3.2648. Min Range: -3.2648

Max Act: 3.1075. Min Act: -0.1700

Data Index: 1083566 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 3.2648. Min Range: -3.2648

Max Act: 3.1075. Min Act: -0.1700

Data Index: 1317829 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 3.2648. Min Range: -3.2648

Max Act: 3.1075. Min Act: -0.1700

Data Index: 1248610 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 3.2648. Min Range: -3.2648

Max Act: 3.1075. Min Act: -0.1700

Data Index: 616436 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 3.2648. Min Range: -3.2648

Max Act: 3.0917. Min Act: -0.1700

Data Index: 597538 (C4 (Web Text))

Max Activating Token Index: 10