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

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

Neuron 1643 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.2654. Min Act: -0.1700

Data Index: 1336674 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.2497. Min Act: -0.1700

Data Index: 126049 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.2340. Min Act: -0.1700

Data Index: 912812 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.2182. Min Act: -0.1700

Data Index: 1252377 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1868. Min Act: -0.1700

Data Index: 605471 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.2025. Min Act: -0.1700

Data Index: 517621 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.2025. Min Act: -0.1700

Data Index: 719617 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.2025. Min Act: -0.1700

Data Index: 1157605 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1868. Min Act: -0.1700

Data Index: 257553 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1710. Min Act: -0.1700

Data Index: 432687 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1868. Min Act: -0.1700

Data Index: 1113797 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1710. Min Act: -0.1700

Data Index: 51159 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1710. Min Act: -0.1700

Data Index: 667085 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1553. Min Act: -0.1700

Data Index: 1350483 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1710. Min Act: -0.1700

Data Index: 1328459 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1238. Min Act: -0.1700

Data Index: 1097953 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1553. Min Act: -0.1700

Data Index: 1211049 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1553. Min Act: -0.1700

Data Index: 280259 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1395. Min Act: -0.1700

Data Index: 261677 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1395. Min Act: -0.1700

Data Index: 111657 (C4 (Web Text))

Max Activating Token Index: 900