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

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

Neuron 115 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.2259. Min Act: -0.1700

Data Index: 590213 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.1945. Min Act: -0.1700

Data Index: 383042 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.1945. Min Act: -0.1700

Data Index: 466717 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.1945. Min Act: -0.1700

Data Index: 882632 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.1945. Min Act: -0.1700

Data Index: 512815 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.1630. Min Act: -0.1700

Data Index: 1475307 (Python Code)

Max Activating Token Index: 784

Text #6

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.1787. Min Act: -0.1700

Data Index: 422559 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.1472. Min Act: -0.1700

Data Index: 1276743 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.1787. Min Act: -0.1700

Data Index: 1073354 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.1787. Min Act: -0.1700

Data Index: 582257 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.1157. Min Act: -0.1700

Data Index: 888895 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.1315. Min Act: -0.1700

Data Index: 1619919 (Python Code)

Max Activating Token Index: 518

Text #12

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.1000. Min Act: -0.1700

Data Index: 705014 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.1157. Min Act: -0.1700

Data Index: 626531 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.1000. Min Act: -0.1700

Data Index: 64853 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.1157. Min Act: -0.1700

Data Index: 1289312 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.1157. Min Act: -0.1700

Data Index: 352149 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.1157. Min Act: -0.1700

Data Index: 821621 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.1000. Min Act: -0.1700

Data Index: 440974 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 3.2259. Min Range: -3.2259

Max Act: 3.0842. Min Act: -0.1700

Data Index: 139908 (C4 (Web Text))

Max Activating Token Index: 994