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

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

Neuron 169 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: 3.6469. Min Range: -3.6469

Max Act: 3.6469. Min Act: -0.1700

Data Index: 505619 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 3.6469. Min Range: -3.6469

Max Act: 3.6469. Min Act: -0.1700

Data Index: 877946 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 3.6469. Min Range: -3.6469

Max Act: 3.5529. Min Act: -0.1700

Data Index: 613640 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 3.6469. Min Range: -3.6469

Max Act: 3.5216. Min Act: -0.1700

Data Index: 189030 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 3.6469. Min Range: -3.6469

Max Act: 3.4903. Min Act: -0.1700

Data Index: 1287242 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 3.6469. Min Range: -3.6469

Max Act: 3.4432. Min Act: -0.1700

Data Index: 159068 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 3.6469. Min Range: -3.6469

Max Act: 3.4746. Min Act: -0.1700

Data Index: 409357 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 3.6469. Min Range: -3.6469

Max Act: 3.4589. Min Act: -0.1700

Data Index: 1046785 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 3.6469. Min Range: -3.6469

Max Act: 3.4432. Min Act: -0.1700

Data Index: 901076 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 3.6469. Min Range: -3.6469

Max Act: 3.3962. Min Act: -0.1700

Data Index: 423140 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 3.6469. Min Range: -3.6469

Max Act: 3.3805. Min Act: -0.1700

Data Index: 1323280 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 3.6469. Min Range: -3.6469

Max Act: 3.3805. Min Act: -0.1700

Data Index: 546316 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 3.6469. Min Range: -3.6469

Max Act: 3.3962. Min Act: -0.1700

Data Index: 166162 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 3.6469. Min Range: -3.6469

Max Act: 3.3805. Min Act: -0.1700

Data Index: 117987 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 3.6469. Min Range: -3.6469

Max Act: 3.3805. Min Act: -0.1700

Data Index: 1009893 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 3.6469. Min Range: -3.6469

Max Act: 3.3648. Min Act: -0.1700

Data Index: 27681 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 3.6469. Min Range: -3.6469

Max Act: 3.3648. Min Act: -0.1700

Data Index: 912649 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 3.6469. Min Range: -3.6469

Max Act: 3.3648. Min Act: -0.1700

Data Index: 190556 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 3.6469. Min Range: -3.6469

Max Act: 3.3805. Min Act: -0.1700

Data Index: 1107525 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 3.6469. Min Range: -3.6469

Max Act: 3.3491. Min Act: -0.1700

Data Index: 747997 (C4 (Web Text))

Max Activating Token Index: 320