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

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

Neuron 164 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: 4.7051. Min Range: -4.7051

Max Act: 4.7051. Min Act: -0.1700

Data Index: 955389 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 4.7051. Min Range: -4.7051

Max Act: 4.2463. Min Act: -0.1700

Data Index: 859311 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 4.7051. Min Range: -4.7051

Max Act: 4.2419. Min Act: -0.1700

Data Index: 946065 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 4.7051. Min Range: -4.7051

Max Act: 4.1875. Min Act: -0.1700

Data Index: 1215011 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 4.7051. Min Range: -4.7051

Max Act: 4.1973. Min Act: -0.1700

Data Index: 688926 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 4.7051. Min Range: -4.7051

Max Act: 4.1689. Min Act: -0.1700

Data Index: 1243426 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 4.7051. Min Range: -4.7051

Max Act: 4.1658. Min Act: -0.1700

Data Index: 1308620 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 4.7051. Min Range: -4.7051

Max Act: 4.1857. Min Act: -0.1700

Data Index: 901127 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 4.7051. Min Range: -4.7051

Max Act: 4.1481. Min Act: -0.1700

Data Index: 936593 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 4.7051. Min Range: -4.7051

Max Act: 4.1582. Min Act: -0.1700

Data Index: 475935 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 4.7051. Min Range: -4.7051

Max Act: 4.1451. Min Act: -0.1700

Data Index: 1350096 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 4.7051. Min Range: -4.7051

Max Act: 4.1655. Min Act: -0.1700

Data Index: 300884 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 4.7051. Min Range: -4.7051

Max Act: 4.1722. Min Act: -0.1700

Data Index: 65324 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 4.7051. Min Range: -4.7051

Max Act: 4.1548. Min Act: -0.1700

Data Index: 524634 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 4.7051. Min Range: -4.7051

Max Act: 4.1631. Min Act: -0.1700

Data Index: 853680 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 4.7051. Min Range: -4.7051

Max Act: 4.1399. Min Act: -0.1700

Data Index: 451197 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 4.7051. Min Range: -4.7051

Max Act: 4.1504. Min Act: -0.1700

Data Index: 842946 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 4.7051. Min Range: -4.7051

Max Act: 4.1506. Min Act: -0.1700

Data Index: 798660 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 4.7051. Min Range: -4.7051

Max Act: 4.1121. Min Act: -0.1700

Data Index: 474754 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 4.7051. Min Range: -4.7051

Max Act: 4.1303. Min Act: -0.1700

Data Index: 1227834 (C4 (Web Text))

Max Activating Token Index: 64