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

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

Neuron 1405 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1653. Min Range: -5.1653

Max Act: 5.1653. Min Act: -0.1700

Data Index: 1094071 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 5.1653. Min Range: -5.1653

Max Act: 5.1028. Min Act: -0.1700

Data Index: 310816 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 5.1653. Min Range: -5.1653

Max Act: 5.0403. Min Act: -0.1700

Data Index: 239904 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 5.1653. Min Range: -5.1653

Max Act: 5.0716. Min Act: -0.1700

Data Index: 1312830 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 5.1653. Min Range: -5.1653

Max Act: 5.0716. Min Act: -0.1700

Data Index: 563809 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 5.1653. Min Range: -5.1653

Max Act: 5.0716. Min Act: -0.1700

Data Index: 1249638 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 5.1653. Min Range: -5.1653

Max Act: 5.0091. Min Act: -0.1700

Data Index: 802983 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 5.1653. Min Range: -5.1653

Max Act: 5.0403. Min Act: -0.1700

Data Index: 1226043 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 5.1653. Min Range: -5.1653

Max Act: 5.0091. Min Act: -0.1700

Data Index: 129489 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 5.1653. Min Range: -5.1653

Max Act: 5.0091. Min Act: -0.1700

Data Index: 1270345 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 5.1653. Min Range: -5.1653

Max Act: 4.9778. Min Act: -0.1700

Data Index: 1030689 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 5.1653. Min Range: -5.1653

Max Act: 5.0716. Min Act: -0.1700

Data Index: 185932 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 5.1653. Min Range: -5.1653

Max Act: 4.9466. Min Act: -0.1700

Data Index: 761300 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 5.1653. Min Range: -5.1653

Max Act: 4.9778. Min Act: -0.1700

Data Index: 359742 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 5.1653. Min Range: -5.1653

Max Act: 5.0091. Min Act: -0.1700

Data Index: 186274 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 5.1653. Min Range: -5.1653

Max Act: 4.9153. Min Act: -0.1700

Data Index: 129455 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 5.1653. Min Range: -5.1653

Max Act: 4.9778. Min Act: -0.1700

Data Index: 1171343 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 5.1653. Min Range: -5.1653

Max Act: 4.9466. Min Act: -0.1700

Data Index: 54929 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 5.1653. Min Range: -5.1653

Max Act: 4.9153. Min Act: -0.1700

Data Index: 206140 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 5.1653. Min Range: -5.1653

Max Act: 4.9466. Min Act: -0.1700

Data Index: 755912 (C4 (Web Text))

Max Activating Token Index: 691