Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 435 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1894. Min Act: -0.1700

Data Index: 8401644 (Open Web Text)

Max Activating Token Index: 1022

Text #1

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1953. Min Act: -0.1338

Data Index: 8416766 (Open Web Text)

Max Activating Token Index: 764

Text #2

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1845. Min Act: -0.1700

Data Index: 3484155 (Open Web Text)

Max Activating Token Index: 667

Text #3

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1732. Min Act: -0.1687

Data Index: 7489201 (Open Web Text)

Max Activating Token Index: 751

Text #4

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1758. Min Act: -0.1700

Data Index: 8031806 (Open Web Text)

Max Activating Token Index: 1004

Text #5

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1868. Min Act: -0.1458

Data Index: 8528720 (Open Web Text)

Max Activating Token Index: 993

Text #6

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1681. Min Act: -0.1699

Data Index: 7410485 (Open Web Text)

Max Activating Token Index: 935

Text #7

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1654. Min Act: -0.1700

Data Index: 1270152 (Open Web Text)

Max Activating Token Index: 588

Text #8

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1662. Min Act: -0.1327

Data Index: 3325837 (Open Web Text)

Max Activating Token Index: 960

Text #9

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1714. Min Act: -0.1694

Data Index: 7177744 (Open Web Text)

Max Activating Token Index: 959

Text #10

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1731. Min Act: -0.1700

Data Index: 601911 (Open Web Text)

Max Activating Token Index: 685

Text #11

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1711. Min Act: -0.1675

Data Index: 3161674 (Open Web Text)

Max Activating Token Index: 993

Text #12

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1695. Min Act: -0.0895

Data Index: 8416769 (Open Web Text)

Max Activating Token Index: 925

Text #13

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1582. Min Act: -0.1460

Data Index: 3325829 (Open Web Text)

Max Activating Token Index: 965

Text #14

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1661. Min Act: -0.1700

Data Index: 3664763 (Open Web Text)

Max Activating Token Index: 982

Text #15

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1554. Min Act: -0.1699

Data Index: 1921620 (Open Web Text)

Max Activating Token Index: 764

Text #16

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1488. Min Act: -0.1557

Data Index: 1175431 (Open Web Text)

Max Activating Token Index: 433

Text #17

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1500. Min Act: -0.1697

Data Index: 7410737 (Open Web Text)

Max Activating Token Index: 704

Text #18

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1589. Min Act: -0.1630

Data Index: 7486176 (Open Web Text)

Max Activating Token Index: 760

Text #19

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1558. Min Act: -0.1686

Data Index: 3965595 (Open Web Text)

Max Activating Token Index: 1021