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

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

Neuron 510 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9345. Min Range: -7.9345

Max Act: 7.9345. Min Act: -0.1700

Data Index: 250257 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 7.9345. Min Range: -7.9345

Max Act: 7.9033. Min Act: -0.1700

Data Index: 1253814 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 7.9345. Min Range: -7.9345

Max Act: 7.4345. Min Act: -0.1700

Data Index: 1437464 (Python Code)

Max Activating Token Index: 302

Text #3

Max Range: 7.9345. Min Range: -7.9345

Max Act: 7.2470. Min Act: -0.1700

Data Index: 1625208 (Python Code)

Max Activating Token Index: 324

Text #4

Max Range: 7.9345. Min Range: -7.9345

Max Act: 7.1533. Min Act: -0.1700

Data Index: 1455593 (Python Code)

Max Activating Token Index: 995

Text #5

Max Range: 7.9345. Min Range: -7.9345

Max Act: 7.1845. Min Act: -0.1700

Data Index: 1561152 (Python Code)

Max Activating Token Index: 52

Text #6

Max Range: 7.9345. Min Range: -7.9345

Max Act: 7.1845. Min Act: -0.1700

Data Index: 69525 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 7.9345. Min Range: -7.9345

Max Act: 7.1533. Min Act: -0.1700

Data Index: 1631808 (Python Code)

Max Activating Token Index: 747

Text #8

Max Range: 7.9345. Min Range: -7.9345

Max Act: 7.1220. Min Act: -0.1700

Data Index: 1362040 (Python Code)

Max Activating Token Index: 783

Text #9

Max Range: 7.9345. Min Range: -7.9345

Max Act: 7.0595. Min Act: -0.1700

Data Index: 1365134 (Python Code)

Max Activating Token Index: 628

Text #10

Max Range: 7.9345. Min Range: -7.9345

Max Act: 7.1220. Min Act: -0.1700

Data Index: 1464796 (Python Code)

Max Activating Token Index: 1016

Text #11

Max Range: 7.9345. Min Range: -7.9345

Max Act: 7.0908. Min Act: -0.1700

Data Index: 694314 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 7.9345. Min Range: -7.9345

Max Act: 7.0908. Min Act: -0.1700

Data Index: 253878 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 7.9345. Min Range: -7.9345

Max Act: 7.0283. Min Act: -0.1700

Data Index: 1608324 (Python Code)

Max Activating Token Index: 747

Text #14

Max Range: 7.9345. Min Range: -7.9345

Max Act: 6.9658. Min Act: -0.1700

Data Index: 713590 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 7.9345. Min Range: -7.9345

Max Act: 6.9033. Min Act: -0.1700

Data Index: 1512004 (Python Code)

Max Activating Token Index: 450

Text #16

Max Range: 7.9345. Min Range: -7.9345

Max Act: 7.0595. Min Act: -0.1700

Data Index: 252199 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 7.9345. Min Range: -7.9345

Max Act: 6.9970. Min Act: -0.1700

Data Index: 1198569 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 7.9345. Min Range: -7.9345

Max Act: 6.9970. Min Act: -0.1700

Data Index: 1409190 (Python Code)

Max Activating Token Index: 709

Text #19

Max Range: 7.9345. Min Range: -7.9345

Max Act: 6.9345. Min Act: -0.1700

Data Index: 1523283 (Python Code)

Max Activating Token Index: 505