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

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

Neuron 758 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: 3.6504. Min Range: -3.6504

Max Act: 3.6504. Min Act: -0.1700

Data Index: 191057 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.6209. Min Act: -0.1686

Data Index: 344662 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.5012. Min Act: -0.1700

Data Index: 1369965 (Python Code)

Max Activating Token Index: 140

Text #3

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.5138. Min Act: -0.1698

Data Index: 607414 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4887. Min Act: -0.1699

Data Index: 666042 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4971. Min Act: -0.1699

Data Index: 342365 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4823. Min Act: -0.1700

Data Index: 316166 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4827. Min Act: -0.1700

Data Index: 208879 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.5015. Min Act: -0.1699

Data Index: 1032919 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4484. Min Act: -0.1699

Data Index: 456020 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4422. Min Act: -0.1700

Data Index: 234187 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4240. Min Act: -0.1700

Data Index: 893535 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4246. Min Act: -0.1700

Data Index: 891791 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4789. Min Act: -0.1696

Data Index: 742734 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.4191. Min Act: -0.1700

Data Index: 403413 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.3516. Min Act: -0.1696

Data Index: 1425735 (Python Code)

Max Activating Token Index: 422

Text #16

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.3812. Min Act: -0.1700

Data Index: 1424471 (Python Code)

Max Activating Token Index: 525

Text #17

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.3582. Min Act: -0.1684

Data Index: 679543 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.3860. Min Act: -0.1700

Data Index: 347819 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 3.6504. Min Range: -3.6504

Max Act: 3.3928. Min Act: -0.1698

Data Index: 1010858 (C4 (Web Text))

Max Activating Token Index: 830