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

Dataset: Open Web Text

Neuron 1989 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: 2.2000. Min Range: -2.2000

Max Act: 2.2000. Min Act: -0.1700

Data Index: 2114083 (Open Web Text)

Max Activating Token Index: 994

Text #1

Max Range: 2.2000. Min Range: -2.2000

Max Act: 2.1557. Min Act: -0.1700

Data Index: 8614134 (Open Web Text)

Max Activating Token Index: 1009

Text #2

Max Range: 2.2000. Min Range: -2.2000

Max Act: 2.1510. Min Act: -0.1700

Data Index: 1153410 (Open Web Text)

Max Activating Token Index: 548

Text #3

Max Range: 2.2000. Min Range: -2.2000

Max Act: 2.1437. Min Act: -0.1700

Data Index: 327084 (Open Web Text)

Max Activating Token Index: 531

Text #4

Max Range: 2.2000. Min Range: -2.2000

Max Act: 2.1473. Min Act: -0.1700

Data Index: 3087748 (Open Web Text)

Max Activating Token Index: 530

Text #5

Max Range: 2.2000. Min Range: -2.2000

Max Act: 2.1343. Min Act: -0.1700

Data Index: 8330294 (Open Web Text)

Max Activating Token Index: 562

Text #6

Max Range: 2.2000. Min Range: -2.2000

Max Act: 2.1192. Min Act: -0.1700

Data Index: 8002145 (Open Web Text)

Max Activating Token Index: 825

Text #7

Max Range: 2.2000. Min Range: -2.2000

Max Act: 2.0879. Min Act: -0.1700

Data Index: 638350 (Open Web Text)

Max Activating Token Index: 1008

Text #8

Max Range: 2.2000. Min Range: -2.2000

Max Act: 2.0693. Min Act: -0.1700

Data Index: 267432 (Open Web Text)

Max Activating Token Index: 862

Text #9

Max Range: 2.2000. Min Range: -2.2000

Max Act: 2.0667. Min Act: -0.1700

Data Index: 8651122 (Open Web Text)

Max Activating Token Index: 993

Text #10

Max Range: 2.2000. Min Range: -2.2000

Max Act: 2.0560. Min Act: -0.1700

Data Index: 405099 (Open Web Text)

Max Activating Token Index: 966

Text #11

Max Range: 2.2000. Min Range: -2.2000

Max Act: 2.0381. Min Act: -0.1700

Data Index: 5695811 (Open Web Text)

Max Activating Token Index: 963

Text #12

Max Range: 2.2000. Min Range: -2.2000

Max Act: 2.0496. Min Act: -0.1700

Data Index: 4854466 (Open Web Text)

Max Activating Token Index: 654

Text #13

Max Range: 2.2000. Min Range: -2.2000

Max Act: 2.0280. Min Act: -0.1700

Data Index: 826503 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 2.2000. Min Range: -2.2000

Max Act: 2.0204. Min Act: -0.1700

Data Index: 8320073 (Open Web Text)

Max Activating Token Index: 426

Text #15

Max Range: 2.2000. Min Range: -2.2000

Max Act: 2.0034. Min Act: -0.1700

Data Index: 572835 (Open Web Text)

Max Activating Token Index: 702

Text #16

Max Range: 2.2000. Min Range: -2.2000

Max Act: 2.0061. Min Act: -0.1700

Data Index: 7386607 (Open Web Text)

Max Activating Token Index: 252

Text #17

Max Range: 2.2000. Min Range: -2.2000

Max Act: 2.0084. Min Act: -0.1700

Data Index: 3627106 (Open Web Text)

Max Activating Token Index: 858

Text #18

Max Range: 2.2000. Min Range: -2.2000

Max Act: 1.9867. Min Act: -0.1700

Data Index: 5280441 (Open Web Text)

Max Activating Token Index: 634

Text #19

Max Range: 2.2000. Min Range: -2.2000

Max Act: 1.9786. Min Act: -0.1700

Data Index: 7472859 (Open Web Text)

Max Activating Token Index: 1002