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

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

Neuron 288 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: 4.3456. Min Range: -4.3456

Max Act: 4.3456. Min Act: -0.1698

Data Index: 946835 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 4.3456. Min Range: -4.3456

Max Act: 4.2216. Min Act: -0.1699

Data Index: 1371465 (Python Code)

Max Activating Token Index: 833

Text #2

Max Range: 4.3456. Min Range: -4.3456

Max Act: 4.1654. Min Act: -0.1035

Data Index: 1408758 (Python Code)

Max Activating Token Index: 296

Text #3

Max Range: 4.3456. Min Range: -4.3456

Max Act: 4.1333. Min Act: -0.1639

Data Index: 1501126 (Python Code)

Max Activating Token Index: 530

Text #4

Max Range: 4.3456. Min Range: -4.3456

Max Act: 4.0882. Min Act: -0.1700

Data Index: 1387871 (Python Code)

Max Activating Token Index: 114

Text #5

Max Range: 4.3456. Min Range: -4.3456

Max Act: 4.1177. Min Act: -0.1035

Data Index: 1424531 (Python Code)

Max Activating Token Index: 71

Text #6

Max Range: 4.3456. Min Range: -4.3456

Max Act: 4.0883. Min Act: -0.1658

Data Index: 1530141 (Python Code)

Max Activating Token Index: 581

Text #7

Max Range: 4.3456. Min Range: -4.3456

Max Act: 4.0574. Min Act: -0.1679

Data Index: 1549111 (Python Code)

Max Activating Token Index: 146

Text #8

Max Range: 4.3456. Min Range: -4.3456

Max Act: 4.0473. Min Act: -0.1275

Data Index: 1592288 (Python Code)

Max Activating Token Index: 622

Text #9

Max Range: 4.3456. Min Range: -4.3456

Max Act: 4.0331. Min Act: -0.1035

Data Index: 1363725 (Python Code)

Max Activating Token Index: 948

Text #10

Max Range: 4.3456. Min Range: -4.3456

Max Act: 4.0116. Min Act: -0.1699

Data Index: 1458234 (Python Code)

Max Activating Token Index: 758

Text #11

Max Range: 4.3456. Min Range: -4.3456

Max Act: 3.9828. Min Act: -0.1495

Data Index: 1652348 (Python Code)

Max Activating Token Index: 73

Text #12

Max Range: 4.3456. Min Range: -4.3456

Max Act: 3.9472. Min Act: -0.1700

Data Index: 1498438 (Python Code)

Max Activating Token Index: 753

Text #13

Max Range: 4.3456. Min Range: -4.3456

Max Act: 3.9153. Min Act: -0.1697

Data Index: 809455 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 4.3456. Min Range: -4.3456

Max Act: 3.9196. Min Act: -0.1700

Data Index: 1598509 (Python Code)

Max Activating Token Index: 953

Text #15

Max Range: 4.3456. Min Range: -4.3456

Max Act: 3.9281. Min Act: -0.1696

Data Index: 1514507 (Python Code)

Max Activating Token Index: 89

Text #16

Max Range: 4.3456. Min Range: -4.3456

Max Act: 3.9248. Min Act: -0.1699

Data Index: 1441408 (Python Code)

Max Activating Token Index: 652

Text #17

Max Range: 4.3456. Min Range: -4.3456

Max Act: 3.9029. Min Act: -0.1661

Data Index: 1547932 (Python Code)

Max Activating Token Index: 926

Text #18

Max Range: 4.3456. Min Range: -4.3456

Max Act: 3.9262. Min Act: -0.1700

Data Index: 1530582 (Python Code)

Max Activating Token Index: 130

Text #19

Max Range: 4.3456. Min Range: -4.3456

Max Act: 3.9030. Min Act: -0.1700

Data Index: 1066324 (C4 (Web Text))

Max Activating Token Index: 761