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

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

Neuron 1668 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2430. Min Range: -5.2430

Max Act: 5.2430. Min Act: -0.1700

Data Index: 291412 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 5.2430. Min Range: -5.2430

Max Act: 5.2430. Min Act: -0.1700

Data Index: 1206699 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 5.2430. Min Range: -5.2430

Max Act: 5.1180. Min Act: -0.1700

Data Index: 1083126 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 5.2430. Min Range: -5.2430

Max Act: 5.1180. Min Act: -0.1700

Data Index: 382698 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 5.2430. Min Range: -5.2430

Max Act: 5.1180. Min Act: -0.1700

Data Index: 491106 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 5.2430. Min Range: -5.2430

Max Act: 5.0242. Min Act: -0.1700

Data Index: 738231 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 5.2430. Min Range: -5.2430

Max Act: 5.0555. Min Act: -0.1700

Data Index: 1161464 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 5.2430. Min Range: -5.2430

Max Act: 5.0555. Min Act: -0.1700

Data Index: 998944 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 5.2430. Min Range: -5.2430

Max Act: 5.0867. Min Act: -0.1700

Data Index: 1146371 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 5.2430. Min Range: -5.2430

Max Act: 4.9617. Min Act: -0.1700

Data Index: 333299 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 5.2430. Min Range: -5.2430

Max Act: 4.9305. Min Act: -0.1700

Data Index: 681165 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 5.2430. Min Range: -5.2430

Max Act: 4.9617. Min Act: -0.1700

Data Index: 1243751 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 5.2430. Min Range: -5.2430

Max Act: 4.9930. Min Act: -0.1700

Data Index: 758310 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 5.2430. Min Range: -5.2430

Max Act: 4.9617. Min Act: -0.1700

Data Index: 288845 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 5.2430. Min Range: -5.2430

Max Act: 4.9305. Min Act: -0.1700

Data Index: 1190392 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 5.2430. Min Range: -5.2430

Max Act: 4.9617. Min Act: -0.1700

Data Index: 396781 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 5.2430. Min Range: -5.2430

Max Act: 4.9305. Min Act: -0.1700

Data Index: 1139343 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 5.2430. Min Range: -5.2430

Max Act: 4.8992. Min Act: -0.1700

Data Index: 932214 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 5.2430. Min Range: -5.2430

Max Act: 4.9930. Min Act: -0.1700

Data Index: 538871 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 5.2430. Min Range: -5.2430

Max Act: 4.8992. Min Act: -0.1700

Data Index: 635334 (C4 (Web Text))

Max Activating Token Index: 749