Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 609 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.7715. Min Act: -0.1700

Data Index: 1204576 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.7510. Min Act: -0.1700

Data Index: 1174107 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.7227. Min Act: -0.1700

Data Index: 939686 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.7013. Min Act: -0.1700

Data Index: 768904 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.6712. Min Act: -0.1700

Data Index: 565337 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.6468. Min Act: -0.1700

Data Index: 337742 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.6487. Min Act: -0.1700

Data Index: 893141 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.6327. Min Act: -0.1700

Data Index: 1004727 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.6443. Min Act: -0.1700

Data Index: 1358610 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.6010. Min Act: -0.1700

Data Index: 545910 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.6030. Min Act: -0.1700

Data Index: 662333 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.5897. Min Act: -0.1700

Data Index: 1156336 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.5568. Min Act: -0.1700

Data Index: 737708 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.5789. Min Act: -0.1700

Data Index: 218551 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.5858. Min Act: -0.1700

Data Index: 449668 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.5845. Min Act: -0.1700

Data Index: 324411 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.5599. Min Act: -0.1700

Data Index: 380357 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.5638. Min Act: -0.1700

Data Index: 67193 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.5862. Min Act: -0.1700

Data Index: 553283 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 3.7715. Min Range: -3.7715

Max Act: 3.5478. Min Act: -0.1700

Data Index: 1042682 (C4 (Web Text))

Max Activating Token Index: 752