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

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

Neuron 1902 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0643. Min Range: -3.0643

Max Act: 3.0643. Min Act: -0.1700

Data Index: 1185189 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 3.0643. Min Range: -3.0643

Max Act: 3.0485. Min Act: -0.1700

Data Index: 458823 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 3.0643. Min Range: -3.0643

Max Act: 3.0485. Min Act: -0.1700

Data Index: 626466 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 3.0643. Min Range: -3.0643

Max Act: 3.0327. Min Act: -0.1700

Data Index: 317128 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 3.0643. Min Range: -3.0643

Max Act: 3.0485. Min Act: -0.1700

Data Index: 1296183 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 3.0643. Min Range: -3.0643

Max Act: 3.0327. Min Act: -0.1700

Data Index: 1264762 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 3.0643. Min Range: -3.0643

Max Act: 3.0327. Min Act: -0.1700

Data Index: 285361 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 3.0643. Min Range: -3.0643

Max Act: 3.0011. Min Act: -0.1700

Data Index: 390982 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 3.0643. Min Range: -3.0643

Max Act: 2.9694. Min Act: -0.1700

Data Index: 786169 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 3.0643. Min Range: -3.0643

Max Act: 2.9694. Min Act: -0.1700

Data Index: 872062 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 3.0643. Min Range: -3.0643

Max Act: 2.9694. Min Act: -0.1700

Data Index: 329180 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 3.0643. Min Range: -3.0643

Max Act: 2.9536. Min Act: -0.1700

Data Index: 355964 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 3.0643. Min Range: -3.0643

Max Act: 2.9536. Min Act: -0.1700

Data Index: 238424 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 3.0643. Min Range: -3.0643

Max Act: 2.9536. Min Act: -0.1700

Data Index: 874509 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 3.0643. Min Range: -3.0643

Max Act: 2.9219. Min Act: -0.1700

Data Index: 1540023 (Python Code)

Max Activating Token Index: 141

Text #15

Max Range: 3.0643. Min Range: -3.0643

Max Act: 2.9219. Min Act: -0.1700

Data Index: 570586 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 3.0643. Min Range: -3.0643

Max Act: 2.9378. Min Act: -0.1700

Data Index: 873772 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 3.0643. Min Range: -3.0643

Max Act: 2.9378. Min Act: -0.1700

Data Index: 1249102 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 3.0643. Min Range: -3.0643

Max Act: 2.9378. Min Act: -0.1700

Data Index: 1019936 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 3.0643. Min Range: -3.0643

Max Act: 2.9219. Min Act: -0.1700

Data Index: 91527 (C4 (Web Text))

Max Activating Token Index: 618