Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1828 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.8663. Min Act: -0.1700

Data Index: 380314 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.7412. Min Act: -0.1700

Data Index: 316757 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.6786. Min Act: -0.1700

Data Index: 1111603 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.7099. Min Act: -0.1700

Data Index: 587906 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.7099. Min Act: -0.1700

Data Index: 1227758 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.7099. Min Act: -0.1700

Data Index: 352092 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.6786. Min Act: -0.1700

Data Index: 1335222 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.6786. Min Act: -0.1700

Data Index: 387554 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.6786. Min Act: -0.1700

Data Index: 1050687 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.6160. Min Act: -0.1700

Data Index: 545262 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.6473. Min Act: -0.1700

Data Index: 152900 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.6786. Min Act: -0.1700

Data Index: 65879 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.7099. Min Act: -0.1700

Data Index: 384500 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.6786. Min Act: -0.1700

Data Index: 11603 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.6786. Min Act: -0.1700

Data Index: 339653 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.6786. Min Act: -0.1700

Data Index: 214425 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.5846. Min Act: -0.1700

Data Index: 1015509 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.6160. Min Act: -0.1700

Data Index: 441139 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.6160. Min Act: -0.1700

Data Index: 259925 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 3.8663. Min Range: -3.8663

Max Act: 3.5846. Min Act: -0.1700

Data Index: 856829 (C4 (Web Text))

Max Activating Token Index: 340