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

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

Neuron 295 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: 3.0510. Min Range: -3.0510

Max Act: 3.0510. Min Act: -0.1693

Data Index: 1620715 (Python Code)

Max Activating Token Index: 830

Text #1

Max Range: 3.0510. Min Range: -3.0510

Max Act: 3.0372. Min Act: -0.1699

Data Index: 1586700 (Python Code)

Max Activating Token Index: 160

Text #2

Max Range: 3.0510. Min Range: -3.0510

Max Act: 3.0179. Min Act: -0.1700

Data Index: 1424863 (Python Code)

Max Activating Token Index: 827

Text #3

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.9886. Min Act: -0.1646

Data Index: 1384333 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.9545. Min Act: -0.1700

Data Index: 1545338 (Python Code)

Max Activating Token Index: 110

Text #5

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.9782. Min Act: -0.1700

Data Index: 1626905 (Python Code)

Max Activating Token Index: 819

Text #6

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.9286. Min Act: -0.1700

Data Index: 1414221 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.9094. Min Act: -0.1700

Data Index: 1535693 (Python Code)

Max Activating Token Index: 816

Text #8

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.8907. Min Act: -0.1700

Data Index: 1462852 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.8889. Min Act: -0.1696

Data Index: 1529789 (Python Code)

Max Activating Token Index: 939

Text #10

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.8980. Min Act: -0.1698

Data Index: 1360262 (Python Code)

Max Activating Token Index: 250

Text #11

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.9025. Min Act: -0.1698

Data Index: 1562080 (Python Code)

Max Activating Token Index: 439

Text #12

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.8824. Min Act: -0.1699

Data Index: 723614 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.8636. Min Act: -0.1700

Data Index: 1636896 (Python Code)

Max Activating Token Index: 798

Text #14

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.8652. Min Act: -0.1698

Data Index: 1577064 (Python Code)

Max Activating Token Index: 229

Text #15

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.8665. Min Act: -0.1699

Data Index: 1447490 (Python Code)

Max Activating Token Index: 829

Text #16

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.8792. Min Act: -0.1700

Data Index: 416120 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.8159. Min Act: -0.1700

Data Index: 1360947 (Python Code)

Max Activating Token Index: 830

Text #18

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.8392. Min Act: -0.1700

Data Index: 1449073 (Python Code)

Max Activating Token Index: 467

Text #19

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.8240. Min Act: -0.1699

Data Index: 1570808 (Python Code)

Max Activating Token Index: 438