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

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

Neuron 2031 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: 3.0645. Min Range: -3.0645

Max Act: 3.0645. Min Act: -0.1700

Data Index: 1579560 (Python Code)

Max Activating Token Index: 687

Text #1

Max Range: 3.0645. Min Range: -3.0645

Max Act: 3.0303. Min Act: -0.1700

Data Index: 1091473 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.9978. Min Act: -0.1700

Data Index: 969577 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 3.0645. Min Range: -3.0645

Max Act: 3.0021. Min Act: -0.1700

Data Index: 106062 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.9555. Min Act: -0.1700

Data Index: 1330611 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.9757. Min Act: -0.1700

Data Index: 1010894 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.9511. Min Act: -0.1700

Data Index: 1311779 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.9561. Min Act: -0.1700

Data Index: 1274250 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.9311. Min Act: -0.1700

Data Index: 66032 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.9337. Min Act: -0.1700

Data Index: 1263429 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.9403. Min Act: -0.1700

Data Index: 633840 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.9152. Min Act: -0.1700

Data Index: 1002946 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.9205. Min Act: -0.1700

Data Index: 245236 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.8995. Min Act: -0.1700

Data Index: 1562899 (Python Code)

Max Activating Token Index: 714

Text #14

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.8974. Min Act: -0.1700

Data Index: 1124598 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.8807. Min Act: -0.1700

Data Index: 1204591 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.8876. Min Act: -0.1700

Data Index: 435206 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.9047. Min Act: -0.1700

Data Index: 1396393 (Python Code)

Max Activating Token Index: 587

Text #18

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.8930. Min Act: -0.1700

Data Index: 1587982 (Python Code)

Max Activating Token Index: 538

Text #19

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.8798. Min Act: -0.1700

Data Index: 564463 (C4 (Web Text))

Max Activating Token Index: 187