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

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

Neuron 230 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: 3.1456. Min Range: -3.1456

Max Act: 3.1456. Min Act: -0.1699

Data Index: 896327 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0508. Min Act: -0.1700

Data Index: 477195 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0417. Min Act: -0.1688

Data Index: 1380768 (Python Code)

Max Activating Token Index: 748

Text #3

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0375. Min Act: -0.1699

Data Index: 354896 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0139. Min Act: -0.1700

Data Index: 1383868 (Python Code)

Max Activating Token Index: 192

Text #5

Max Range: 3.1456. Min Range: -3.1456

Max Act: 2.9969. Min Act: -0.1700

Data Index: 964190 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0034. Min Act: -0.1695

Data Index: 1467708 (Python Code)

Max Activating Token Index: 652

Text #7

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0006. Min Act: -0.1693

Data Index: 121875 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 3.1456. Min Range: -3.1456

Max Act: 2.9818. Min Act: -0.1700

Data Index: 1078448 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 3.1456. Min Range: -3.1456

Max Act: 2.9706. Min Act: -0.1682

Data Index: 1644496 (Python Code)

Max Activating Token Index: 929

Text #10

Max Range: 3.1456. Min Range: -3.1456

Max Act: 2.9623. Min Act: -0.1700

Data Index: 1542242 (Python Code)

Max Activating Token Index: 814

Text #11

Max Range: 3.1456. Min Range: -3.1456

Max Act: 2.9450. Min Act: -0.1700

Data Index: 489749 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 3.1456. Min Range: -3.1456

Max Act: 2.9504. Min Act: -0.1700

Data Index: 1630921 (Python Code)

Max Activating Token Index: 960

Text #13

Max Range: 3.1456. Min Range: -3.1456

Max Act: 2.9652. Min Act: -0.1691

Data Index: 1267321 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 3.1456. Min Range: -3.1456

Max Act: 2.9229. Min Act: -0.1700

Data Index: 1018009 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 3.1456. Min Range: -3.1456

Max Act: 2.9381. Min Act: -0.1700

Data Index: 1489891 (Python Code)

Max Activating Token Index: 795

Text #16

Max Range: 3.1456. Min Range: -3.1456

Max Act: 2.9416. Min Act: -0.1700

Data Index: 1525981 (Python Code)

Max Activating Token Index: 461

Text #17

Max Range: 3.1456. Min Range: -3.1456

Max Act: 2.9401. Min Act: -0.1700

Data Index: 1465885 (Python Code)

Max Activating Token Index: 689

Text #18

Max Range: 3.1456. Min Range: -3.1456

Max Act: 2.9250. Min Act: -0.1700

Data Index: 1539578 (Python Code)

Max Activating Token Index: 883

Text #19

Max Range: 3.1456. Min Range: -3.1456

Max Act: 2.9437. Min Act: -0.1699

Data Index: 1516149 (Python Code)

Max Activating Token Index: 568