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

Dataset: Open Web Text

Neuron 1612 in Layer 5

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: 4.3882. Min Range: -4.3882

Max Act: 4.3882. Min Act: -0.1700

Data Index: 1901045 (Open Web Text)

Max Activating Token Index: 553

Text #1

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.3071. Min Act: -0.1700

Data Index: 7633949 (Open Web Text)

Max Activating Token Index: 404

Text #2

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.2696. Min Act: -0.1700

Data Index: 6995959 (Open Web Text)

Max Activating Token Index: 620

Text #3

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.2179. Min Act: -0.1700

Data Index: 2834156 (Open Web Text)

Max Activating Token Index: 383

Text #4

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.2322. Min Act: -0.1700

Data Index: 6458988 (Open Web Text)

Max Activating Token Index: 873

Text #5

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1967. Min Act: -0.1700

Data Index: 7615862 (Open Web Text)

Max Activating Token Index: 542

Text #6

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1956. Min Act: -0.1700

Data Index: 250 (Open Web Text)

Max Activating Token Index: 593

Text #7

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1556. Min Act: -0.1700

Data Index: 1729454 (Open Web Text)

Max Activating Token Index: 352

Text #8

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1529. Min Act: -0.1700

Data Index: 5941184 (Open Web Text)

Max Activating Token Index: 884

Text #9

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1511. Min Act: -0.1700

Data Index: 330033 (Open Web Text)

Max Activating Token Index: 319

Text #10

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1457. Min Act: -0.1700

Data Index: 6486839 (Open Web Text)

Max Activating Token Index: 223

Text #11

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1583. Min Act: -0.1700

Data Index: 7767268 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1240. Min Act: -0.1700

Data Index: 1899197 (Open Web Text)

Max Activating Token Index: 878

Text #13

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1229. Min Act: -0.1700

Data Index: 1109339 (Open Web Text)

Max Activating Token Index: 675

Text #14

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.0895. Min Act: -0.1700

Data Index: 5927324 (Open Web Text)

Max Activating Token Index: 649

Text #15

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1148. Min Act: -0.1700

Data Index: 3287345 (Open Web Text)

Max Activating Token Index: 136

Text #16

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.0858. Min Act: -0.1700

Data Index: 3575215 (Open Web Text)

Max Activating Token Index: 617

Text #17

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.0707. Min Act: -0.1700

Data Index: 6979395 (Open Web Text)

Max Activating Token Index: 389

Text #18

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.0848. Min Act: -0.1700

Data Index: 732481 (Open Web Text)

Max Activating Token Index: 550

Text #19

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.0775. Min Act: -0.1700

Data Index: 4420460 (Open Web Text)

Max Activating Token Index: 982