Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 257 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.0000. Min Range: -4.0000

Max Act: 3.9687. Min Act: -0.1700

Data Index: 1013241 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 4.0000. Min Range: -4.0000

Max Act: 4.0000. Min Act: -0.1700

Data Index: 1161198 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 4.0000. Min Range: -4.0000

Max Act: 3.9687. Min Act: -0.1700

Data Index: 139433 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 4.0000. Min Range: -4.0000

Max Act: 3.9687. Min Act: -0.1700

Data Index: 627568 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 4.0000. Min Range: -4.0000

Max Act: 3.9687. Min Act: -0.1700

Data Index: 916574 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 4.0000. Min Range: -4.0000

Max Act: 3.9687. Min Act: -0.1700

Data Index: 1343414 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 4.0000. Min Range: -4.0000

Max Act: 3.9375. Min Act: -0.1700

Data Index: 1326615 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 4.0000. Min Range: -4.0000

Max Act: 3.9375. Min Act: -0.1700

Data Index: 1180861 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 4.0000. Min Range: -4.0000

Max Act: 3.9375. Min Act: -0.1700

Data Index: 1342706 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 4.0000. Min Range: -4.0000

Max Act: 3.9062. Min Act: -0.1700

Data Index: 303513 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 4.0000. Min Range: -4.0000

Max Act: 3.9375. Min Act: -0.1700

Data Index: 120545 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 4.0000. Min Range: -4.0000

Max Act: 3.9062. Min Act: -0.1700

Data Index: 987204 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 4.0000. Min Range: -4.0000

Max Act: 3.8749. Min Act: -0.1700

Data Index: 401598 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 4.0000. Min Range: -4.0000

Max Act: 3.9062. Min Act: -0.1700

Data Index: 675457 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 4.0000. Min Range: -4.0000

Max Act: 3.8749. Min Act: -0.1700

Data Index: 163480 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 4.0000. Min Range: -4.0000

Max Act: 3.8749. Min Act: -0.1700

Data Index: 1165551 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 4.0000. Min Range: -4.0000

Max Act: 3.8436. Min Act: -0.1700

Data Index: 955825 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 4.0000. Min Range: -4.0000

Max Act: 3.8749. Min Act: -0.1700

Data Index: 710645 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 4.0000. Min Range: -4.0000

Max Act: 3.8124. Min Act: -0.1700

Data Index: 65455 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 4.0000. Min Range: -4.0000

Max Act: 3.8436. Min Act: -0.1700

Data Index: 656472 (C4 (Web Text))

Max Activating Token Index: 358