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

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

Neuron 385 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: 3.3106. Min Range: -3.3106

Max Act: 3.3106. Min Act: -0.1700

Data Index: 1451526 (Python Code)

Max Activating Token Index: 148

Text #1

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.2507. Min Act: -0.1700

Data Index: 270306 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.2260. Min Act: -0.1700

Data Index: 1370268 (Python Code)

Max Activating Token Index: 30

Text #3

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.2082. Min Act: -0.1700

Data Index: 1613334 (Python Code)

Max Activating Token Index: 175

Text #4

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.1611. Min Act: -0.1700

Data Index: 1591734 (Python Code)

Max Activating Token Index: 290

Text #5

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.1749. Min Act: -0.1700

Data Index: 1589610 (Python Code)

Max Activating Token Index: 351

Text #6

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.1271. Min Act: -0.1700

Data Index: 1438757 (Python Code)

Max Activating Token Index: 436

Text #7

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.1248. Min Act: -0.1700

Data Index: 1546599 (Python Code)

Max Activating Token Index: 150

Text #8

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.1135. Min Act: -0.1700

Data Index: 1448829 (Python Code)

Max Activating Token Index: 153

Text #9

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.1209. Min Act: -0.1700

Data Index: 1601567 (Python Code)

Max Activating Token Index: 655

Text #10

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.0963. Min Act: -0.1700

Data Index: 173975 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.1379. Min Act: -0.1700

Data Index: 484210 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.0897. Min Act: -0.1700

Data Index: 1614388 (Python Code)

Max Activating Token Index: 682

Text #13

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.0863. Min Act: -0.1700

Data Index: 1624438 (Python Code)

Max Activating Token Index: 458

Text #14

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.0652. Min Act: -0.1700

Data Index: 1600127 (Python Code)

Max Activating Token Index: 866

Text #15

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.1166. Min Act: -0.1700

Data Index: 1434984 (Python Code)

Max Activating Token Index: 436

Text #16

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.1051. Min Act: -0.1700

Data Index: 1425101 (Python Code)

Max Activating Token Index: 930

Text #17

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.0996. Min Act: -0.1700

Data Index: 1567989 (Python Code)

Max Activating Token Index: 617

Text #18

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.0858. Min Act: -0.1700

Data Index: 1200028 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.0767. Min Act: -0.1700

Data Index: 7581 (C4 (Web Text))

Max Activating Token Index: 391