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

Dataset: Open Web Text

Neuron 1691 in Layer 3

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: 4.1588. Min Range: -4.1588

Max Act: 4.1319. Min Act: -0.1700

Data Index: 2926128 (Open Web Text)

Max Activating Token Index: 772

Text #1

Max Range: 4.1588. Min Range: -4.1588

Max Act: 4.1464. Min Act: -0.1700

Data Index: 7398037 (Open Web Text)

Max Activating Token Index: 679

Text #2

Max Range: 4.1588. Min Range: -4.1588

Max Act: 4.1588. Min Act: -0.1700

Data Index: 7527619 (Open Web Text)

Max Activating Token Index: 858

Text #3

Max Range: 4.1588. Min Range: -4.1588

Max Act: 4.0854. Min Act: -0.1700

Data Index: 1743766 (Open Web Text)

Max Activating Token Index: 507

Text #4

Max Range: 4.1588. Min Range: -4.1588

Max Act: 4.0975. Min Act: -0.1700

Data Index: 570703 (Open Web Text)

Max Activating Token Index: 951

Text #5

Max Range: 4.1588. Min Range: -4.1588

Max Act: 4.0708. Min Act: -0.1700

Data Index: 5520197 (Open Web Text)

Max Activating Token Index: 631

Text #6

Max Range: 4.1588. Min Range: -4.1588

Max Act: 4.0023. Min Act: -0.1700

Data Index: 705349 (Open Web Text)

Max Activating Token Index: 830

Text #7

Max Range: 4.1588. Min Range: -4.1588

Max Act: 4.0464. Min Act: -0.1700

Data Index: 8718813 (Open Web Text)

Max Activating Token Index: 940

Text #8

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9900. Min Act: -0.1700

Data Index: 6122394 (Open Web Text)

Max Activating Token Index: 885

Text #9

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9509. Min Act: -0.1700

Data Index: 60466 (Open Web Text)

Max Activating Token Index: 485

Text #10

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9907. Min Act: -0.1700

Data Index: 630083 (Open Web Text)

Max Activating Token Index: 823

Text #11

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9645. Min Act: -0.1700

Data Index: 3745262 (Open Web Text)

Max Activating Token Index: 418

Text #12

Max Range: 4.1588. Min Range: -4.1588

Max Act: 4.0006. Min Act: -0.1700

Data Index: 3709731 (Open Web Text)

Max Activating Token Index: 1015

Text #13

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9640. Min Act: -0.1700

Data Index: 6645772 (Open Web Text)

Max Activating Token Index: 549

Text #14

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9904. Min Act: -0.1700

Data Index: 6424177 (Open Web Text)

Max Activating Token Index: 65

Text #15

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9327. Min Act: -0.1700

Data Index: 1599489 (Open Web Text)

Max Activating Token Index: 583

Text #16

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9520. Min Act: -0.1700

Data Index: 4262993 (Open Web Text)

Max Activating Token Index: 988

Text #17

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9531. Min Act: -0.1700

Data Index: 4408907 (Open Web Text)

Max Activating Token Index: 289

Text #18

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9386. Min Act: -0.1700

Data Index: 4642509 (Open Web Text)

Max Activating Token Index: 565

Text #19

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9423. Min Act: -0.1700

Data Index: 4774732 (Open Web Text)

Max Activating Token Index: 904