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

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

Neuron 1590 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: 5.7796. Min Range: -5.7796

Max Act: 5.7796. Min Act: -0.1699

Data Index: 1245850 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 5.7796. Min Range: -5.7796

Max Act: 5.7171. Min Act: -0.1700

Data Index: 668480 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 5.7796. Min Range: -5.7796

Max Act: 5.3421. Min Act: -0.1700

Data Index: 350844 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 5.7796. Min Range: -5.7796

Max Act: 5.2796. Min Act: -0.1700

Data Index: 1018021 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 5.7796. Min Range: -5.7796

Max Act: 5.3421. Min Act: -0.1700

Data Index: 287890 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 5.7796. Min Range: -5.7796

Max Act: 5.3108. Min Act: -0.1700

Data Index: 802232 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 5.7796. Min Range: -5.7796

Max Act: 5.3108. Min Act: -0.1700

Data Index: 301818 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 5.7796. Min Range: -5.7796

Max Act: 5.3108. Min Act: -0.1700

Data Index: 466250 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 5.7796. Min Range: -5.7796

Max Act: 5.2483. Min Act: -0.1700

Data Index: 361248 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 5.7796. Min Range: -5.7796

Max Act: 5.2796. Min Act: -0.1700

Data Index: 851494 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 5.7796. Min Range: -5.7796

Max Act: 5.2483. Min Act: -0.1700

Data Index: 297428 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 5.7796. Min Range: -5.7796

Max Act: 5.2171. Min Act: -0.1700

Data Index: 85060 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 5.7796. Min Range: -5.7796

Max Act: 5.2171. Min Act: -0.1700

Data Index: 1077901 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 5.7796. Min Range: -5.7796

Max Act: 5.1858. Min Act: -0.1700

Data Index: 639037 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 5.7796. Min Range: -5.7796

Max Act: 5.2483. Min Act: -0.1700

Data Index: 86007 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 5.7796. Min Range: -5.7796

Max Act: 5.2483. Min Act: -0.1700

Data Index: 795735 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 5.7796. Min Range: -5.7796

Max Act: 5.2171. Min Act: -0.1699

Data Index: 691591 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 5.7796. Min Range: -5.7796

Max Act: 5.1546. Min Act: -0.1700

Data Index: 915023 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 5.7796. Min Range: -5.7796

Max Act: 5.1858. Min Act: -0.1700

Data Index: 506993 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 5.7796. Min Range: -5.7796

Max Act: 5.1858. Min Act: -0.1700

Data Index: 1179698 (C4 (Web Text))

Max Activating Token Index: 590