Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1580 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.1524. Min Act: -0.1700

Data Index: 1210928 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.1209. Min Act: -0.1700

Data Index: 34567 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.0578. Min Act: -0.1700

Data Index: 799943 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.0578. Min Act: -0.1700

Data Index: 1020351 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.0578. Min Act: -0.1700

Data Index: 950546 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.0578. Min Act: -0.1700

Data Index: 52735 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.0420. Min Act: -0.1700

Data Index: 299013 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.0420. Min Act: -0.1700

Data Index: 1160366 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.0578. Min Act: -0.1700

Data Index: 392076 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.0263. Min Act: -0.1700

Data Index: 568687 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.0263. Min Act: -0.1700

Data Index: 1040216 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.0420. Min Act: -0.1700

Data Index: 423101 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.0105. Min Act: -0.1700

Data Index: 1199833 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.0263. Min Act: -0.1700

Data Index: 564139 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.0420. Min Act: -0.1700

Data Index: 45561 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.0263. Min Act: -0.1700

Data Index: 514722 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.0263. Min Act: -0.1700

Data Index: 312646 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.0105. Min Act: -0.1700

Data Index: 382817 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 3.1524. Min Range: -3.1524

Max Act: 2.9946. Min Act: -0.1700

Data Index: 531771 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 3.1524. Min Range: -3.1524

Max Act: 3.0105. Min Act: -0.1700

Data Index: 32463 (C4 (Web Text))

Max Activating Token Index: 498