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

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

Neuron 183 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: 3.3828. Min Range: -3.3828

Max Act: 3.3828. Min Act: -0.1700

Data Index: 537511 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 3.3828. Min Range: -3.3828

Max Act: 3.3828. Min Act: -0.1700

Data Index: 329907 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 3.3828. Min Range: -3.3828

Max Act: 3.3828. Min Act: -0.1700

Data Index: 189143 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 3.3828. Min Range: -3.3828

Max Act: 3.3672. Min Act: -0.1700

Data Index: 1267691 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 3.3828. Min Range: -3.3828

Max Act: 3.3515. Min Act: -0.1700

Data Index: 785722 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 3.3828. Min Range: -3.3828

Max Act: 3.3515. Min Act: -0.1700

Data Index: 30042 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 3.3828. Min Range: -3.3828

Max Act: 3.3201. Min Act: -0.1700

Data Index: 475171 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 3.3828. Min Range: -3.3828

Max Act: 3.3201. Min Act: -0.1700

Data Index: 199977 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 3.3828. Min Range: -3.3828

Max Act: 3.3044. Min Act: -0.1700

Data Index: 370855 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 3.3828. Min Range: -3.3828

Max Act: 3.3201. Min Act: -0.1700

Data Index: 1331586 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 3.3828. Min Range: -3.3828

Max Act: 3.3201. Min Act: -0.1700

Data Index: 1358386 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 3.3828. Min Range: -3.3828

Max Act: 3.2729. Min Act: -0.1700

Data Index: 637726 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 3.3828. Min Range: -3.3828

Max Act: 3.2729. Min Act: -0.1700

Data Index: 1027463 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 3.3828. Min Range: -3.3828

Max Act: 3.2729. Min Act: -0.1700

Data Index: 1096343 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 3.3828. Min Range: -3.3828

Max Act: 3.2572. Min Act: -0.1700

Data Index: 477544 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 3.3828. Min Range: -3.3828

Max Act: 3.2572. Min Act: -0.1700

Data Index: 109273 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 3.3828. Min Range: -3.3828

Max Act: 3.2572. Min Act: -0.1700

Data Index: 598651 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 3.3828. Min Range: -3.3828

Max Act: 3.2415. Min Act: -0.1700

Data Index: 314598 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 3.3828. Min Range: -3.3828

Max Act: 3.2258. Min Act: -0.1700

Data Index: 1055593 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 3.3828. Min Range: -3.3828

Max Act: 3.2258. Min Act: -0.1700

Data Index: 267248 (C4 (Web Text))

Max Activating Token Index: 164