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

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

Neuron 1564 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1574. Min Range: -5.1574

Max Act: 5.1574. Min Act: -0.1700

Data Index: 336228 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 5.1574. Min Range: -5.1574

Max Act: 5.1262. Min Act: -0.1700

Data Index: 433850 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 5.1574. Min Range: -5.1574

Max Act: 5.0637. Min Act: -0.1700

Data Index: 330650 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 5.1574. Min Range: -5.1574

Max Act: 4.9074. Min Act: -0.1700

Data Index: 1119573 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 5.1574. Min Range: -5.1574

Max Act: 5.0012. Min Act: -0.1700

Data Index: 1235572 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 5.1574. Min Range: -5.1574

Max Act: 4.9699. Min Act: -0.1700

Data Index: 299182 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 5.1574. Min Range: -5.1574

Max Act: 4.9699. Min Act: -0.1700

Data Index: 1006082 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 5.1574. Min Range: -5.1574

Max Act: 4.8762. Min Act: -0.1700

Data Index: 487898 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 5.1574. Min Range: -5.1574

Max Act: 4.9074. Min Act: -0.1700

Data Index: 970585 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 5.1574. Min Range: -5.1574

Max Act: 4.8762. Min Act: -0.1700

Data Index: 970933 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 5.1574. Min Range: -5.1574

Max Act: 4.9387. Min Act: -0.1700

Data Index: 650795 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 5.1574. Min Range: -5.1574

Max Act: 4.9074. Min Act: -0.1700

Data Index: 589472 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 5.1574. Min Range: -5.1574

Max Act: 4.9074. Min Act: -0.1700

Data Index: 1314365 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 5.1574. Min Range: -5.1574

Max Act: 4.9387. Min Act: -0.1700

Data Index: 1303162 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 5.1574. Min Range: -5.1574

Max Act: 4.9074. Min Act: -0.1700

Data Index: 1239536 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 5.1574. Min Range: -5.1574

Max Act: 4.9074. Min Act: -0.1700

Data Index: 637597 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 5.1574. Min Range: -5.1574

Max Act: 4.8762. Min Act: -0.1700

Data Index: 1091140 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 5.1574. Min Range: -5.1574

Max Act: 4.8449. Min Act: -0.1700

Data Index: 1105423 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 5.1574. Min Range: -5.1574

Max Act: 4.8449. Min Act: -0.1700

Data Index: 168717 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 5.1574. Min Range: -5.1574

Max Act: 4.9074. Min Act: -0.1700

Data Index: 630400 (C4 (Web Text))

Max Activating Token Index: 664