Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1039 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.2265. Min Act: -0.1700

Data Index: 168436 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.1950. Min Act: -0.1700

Data Index: 848354 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.2265. Min Act: -0.1700

Data Index: 1264701 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.1950. Min Act: -0.1700

Data Index: 838501 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.1950. Min Act: -0.1700

Data Index: 965707 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.1320. Min Act: -0.1700

Data Index: 1335433 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.1005. Min Act: -0.1700

Data Index: 358480 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0690. Min Act: -0.1700

Data Index: 1072247 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0532. Min Act: -0.1700

Data Index: 1288135 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0847. Min Act: -0.1700

Data Index: 258435 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0690. Min Act: -0.1700

Data Index: 1138876 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0847. Min Act: -0.1700

Data Index: 311208 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0058. Min Act: -0.1700

Data Index: 317756 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0058. Min Act: -0.1700

Data Index: 946323 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0374. Min Act: -0.1700

Data Index: 935456 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0532. Min Act: -0.1700

Data Index: 570605 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0532. Min Act: -0.1700

Data Index: 333784 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0058. Min Act: -0.1700

Data Index: 20709 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0532. Min Act: -0.1700

Data Index: 1124413 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 3.2265. Min Range: -3.2265

Max Act: 3.0216. Min Act: -0.1700

Data Index: 635505 (C4 (Web Text))

Max Activating Token Index: 394