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

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

Neuron 1694 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.5167. Min Act: -0.1700

Data Index: 732099 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.4540. Min Act: -0.1700

Data Index: 1178512 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.4540. Min Act: -0.1700

Data Index: 192452 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.2657. Min Act: -0.1700

Data Index: 470474 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.2342. Min Act: -0.1700

Data Index: 1333360 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.1713. Min Act: -0.1700

Data Index: 1141449 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.2028. Min Act: -0.1700

Data Index: 194381 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.2342. Min Act: -0.1700

Data Index: 1209942 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.2657. Min Act: -0.1700

Data Index: 858338 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.2657. Min Act: -0.1700

Data Index: 1249391 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.1713. Min Act: -0.1700

Data Index: 803288 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.1713. Min Act: -0.1700

Data Index: 773849 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.1398. Min Act: -0.1700

Data Index: 583536 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.1713. Min Act: -0.1700

Data Index: 742499 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.1713. Min Act: -0.1700

Data Index: 152810 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.1713. Min Act: -0.1700

Data Index: 834731 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.1398. Min Act: -0.1700

Data Index: 1314807 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.1083. Min Act: -0.1700

Data Index: 1170790 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.1398. Min Act: -0.1700

Data Index: 1175354 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 3.5167. Min Range: -3.5167

Max Act: 3.0768. Min Act: -0.1700

Data Index: 14041 (C4 (Web Text))

Max Activating Token Index: 654