Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 684 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.8193. Min Act: -0.1178

Data Index: 1014629 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.7247. Min Act: -0.1700

Data Index: 739563 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.6556. Min Act: -0.1700

Data Index: 767240 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.6609. Min Act: -0.1178

Data Index: 468818 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.6837. Min Act: -0.1699

Data Index: 121079 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.6562. Min Act: -0.1700

Data Index: 789744 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.6507. Min Act: -0.1700

Data Index: 1005705 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.6514. Min Act: -0.1700

Data Index: 319223 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.6222. Min Act: -0.1700

Data Index: 478825 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.6044. Min Act: -0.1700

Data Index: 533181 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.5985. Min Act: -0.1700

Data Index: 997877 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.5938. Min Act: -0.1700

Data Index: 47418 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.5680. Min Act: -0.1178

Data Index: 566449 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.5740. Min Act: -0.1700

Data Index: 1156869 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.5602. Min Act: -0.1700

Data Index: 551018 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.5763. Min Act: -0.1700

Data Index: 375934 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.5366. Min Act: -0.1700

Data Index: 990263 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.5268. Min Act: -0.1700

Data Index: 179953 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.5371. Min Act: -0.1700

Data Index: 324980 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.5414. Min Act: -0.1700

Data Index: 788551 (C4 (Web Text))

Max Activating Token Index: 820