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

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

Neuron 1797 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: 5.8984. Min Range: -5.8984

Max Act: 5.8984. Min Act: -0.1700

Data Index: 543845 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 5.8984. Min Range: -5.8984

Max Act: 5.6797. Min Act: -0.1700

Data Index: 709241 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 5.8984. Min Range: -5.8984

Max Act: 5.6484. Min Act: -0.1700

Data Index: 1067332 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 5.8984. Min Range: -5.8984

Max Act: 5.6172. Min Act: -0.1700

Data Index: 572814 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 5.8984. Min Range: -5.8984

Max Act: 5.3984. Min Act: -0.1700

Data Index: 902375 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 5.8984. Min Range: -5.8984

Max Act: 5.4609. Min Act: -0.1700

Data Index: 561799 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 5.8984. Min Range: -5.8984

Max Act: 5.3984. Min Act: -0.1700

Data Index: 437235 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 5.8984. Min Range: -5.8984

Max Act: 5.3672. Min Act: -0.1700

Data Index: 878741 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 5.8984. Min Range: -5.8984

Max Act: 5.3359. Min Act: -0.1700

Data Index: 152866 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 5.8984. Min Range: -5.8984

Max Act: 5.3047. Min Act: -0.1700

Data Index: 1023564 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 5.8984. Min Range: -5.8984

Max Act: 5.3359. Min Act: -0.1700

Data Index: 238483 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 5.8984. Min Range: -5.8984

Max Act: 5.3359. Min Act: -0.1700

Data Index: 418959 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 5.8984. Min Range: -5.8984

Max Act: 5.2734. Min Act: -0.1700

Data Index: 758022 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 5.8984. Min Range: -5.8984

Max Act: 5.2734. Min Act: -0.1700

Data Index: 316969 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 5.8984. Min Range: -5.8984

Max Act: 5.3047. Min Act: -0.1700

Data Index: 1330278 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 5.8984. Min Range: -5.8984

Max Act: 5.2422. Min Act: -0.1700

Data Index: 452544 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 5.8984. Min Range: -5.8984

Max Act: 5.2734. Min Act: -0.1700

Data Index: 698327 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 5.8984. Min Range: -5.8984

Max Act: 5.2109. Min Act: -0.1700

Data Index: 504228 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 5.8984. Min Range: -5.8984

Max Act: 5.2109. Min Act: -0.1700

Data Index: 868054 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 5.8984. Min Range: -5.8984

Max Act: 5.2109. Min Act: -0.1700

Data Index: 204882 (C4 (Web Text))

Max Activating Token Index: 929