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

Dataset: Open Web Text

Neuron 744 in Layer 2

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: 2.1792. Min Range: -2.1792

Max Act: 2.1792. Min Act: -0.1700

Data Index: 6454390 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.1792. Min Range: -2.1792

Max Act: 2.1769. Min Act: -0.1700

Data Index: 7383242 (Open Web Text)

Max Activating Token Index: 957

Text #2

Max Range: 2.1792. Min Range: -2.1792

Max Act: 2.1496. Min Act: -0.1700

Data Index: 4182062 (Open Web Text)

Max Activating Token Index: 846

Text #3

Max Range: 2.1792. Min Range: -2.1792

Max Act: 2.1536. Min Act: -0.1700

Data Index: 5085549 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.1792. Min Range: -2.1792

Max Act: 2.1719. Min Act: -0.1700

Data Index: 7016392 (Open Web Text)

Max Activating Token Index: 976

Text #5

Max Range: 2.1792. Min Range: -2.1792

Max Act: 2.1366. Min Act: -0.1700

Data Index: 2608212 (Open Web Text)

Max Activating Token Index: 249

Text #6

Max Range: 2.1792. Min Range: -2.1792

Max Act: 2.1406. Min Act: -0.1700

Data Index: 2346541 (Open Web Text)

Max Activating Token Index: 825

Text #7

Max Range: 2.1792. Min Range: -2.1792

Max Act: 2.1245. Min Act: -0.1700

Data Index: 1770222 (Open Web Text)

Max Activating Token Index: 282

Text #8

Max Range: 2.1792. Min Range: -2.1792

Max Act: 2.1174. Min Act: -0.1700

Data Index: 6403047 (Open Web Text)

Max Activating Token Index: 818

Text #9

Max Range: 2.1792. Min Range: -2.1792

Max Act: 2.1292. Min Act: -0.1700

Data Index: 7571788 (Open Web Text)

Max Activating Token Index: 423

Text #10

Max Range: 2.1792. Min Range: -2.1792

Max Act: 2.1154. Min Act: -0.1700

Data Index: 1822863 (Open Web Text)

Max Activating Token Index: 760

Text #11

Max Range: 2.1792. Min Range: -2.1792

Max Act: 2.1020. Min Act: -0.1700

Data Index: 7159624 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.1792. Min Range: -2.1792

Max Act: 2.1075. Min Act: -0.1700

Data Index: 6744883 (Open Web Text)

Max Activating Token Index: 830

Text #13

Max Range: 2.1792. Min Range: -2.1792

Max Act: 2.1181. Min Act: -0.1700

Data Index: 6763384 (Open Web Text)

Max Activating Token Index: 539

Text #14

Max Range: 2.1792. Min Range: -2.1792

Max Act: 2.1095. Min Act: -0.1700

Data Index: 8262048 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 2.1792. Min Range: -2.1792

Max Act: 2.1022. Min Act: -0.1700

Data Index: 2321410 (Open Web Text)

Max Activating Token Index: 609

Text #16

Max Range: 2.1792. Min Range: -2.1792

Max Act: 2.1038. Min Act: -0.1700

Data Index: 4134283 (Open Web Text)

Max Activating Token Index: 403

Text #17

Max Range: 2.1792. Min Range: -2.1792

Max Act: 2.0791. Min Act: -0.1700

Data Index: 6309177 (Open Web Text)

Max Activating Token Index: 329

Text #18

Max Range: 2.1792. Min Range: -2.1792

Max Act: 2.0895. Min Act: -0.1700

Data Index: 3359284 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.1792. Min Range: -2.1792

Max Act: 2.0857. Min Act: -0.1700

Data Index: 3394017 (Open Web Text)

Max Activating Token Index: 954