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

Dataset: Open Web Text

Neuron 1234 in Layer 4

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: 3.2445. Min Range: -3.2445

Max Act: 3.2445. Min Act: -0.1700

Data Index: 868894 (Open Web Text)

Max Activating Token Index: 484

Text #1

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.2304. Min Act: -0.1700

Data Index: 5621575 (Open Web Text)

Max Activating Token Index: 861

Text #2

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.1478. Min Act: -0.1700

Data Index: 6831691 (Open Web Text)

Max Activating Token Index: 882

Text #3

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.1196. Min Act: -0.1700

Data Index: 13413 (Open Web Text)

Max Activating Token Index: 655

Text #4

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.1153. Min Act: -0.1700

Data Index: 5087623 (Open Web Text)

Max Activating Token Index: 401

Text #5

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.0989. Min Act: -0.1700

Data Index: 682850 (Open Web Text)

Max Activating Token Index: 1002

Text #6

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.0882. Min Act: -0.1700

Data Index: 6544463 (Open Web Text)

Max Activating Token Index: 160

Text #7

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.0931. Min Act: -0.1700

Data Index: 7504958 (Open Web Text)

Max Activating Token Index: 506

Text #8

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.0857. Min Act: -0.1700

Data Index: 7867124 (Open Web Text)

Max Activating Token Index: 597

Text #9

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.0871. Min Act: -0.1700

Data Index: 1067317 (Open Web Text)

Max Activating Token Index: 302

Text #10

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.0986. Min Act: -0.1700

Data Index: 1415410 (Open Web Text)

Max Activating Token Index: 771

Text #11

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.0708. Min Act: -0.1700

Data Index: 5999287 (Open Web Text)

Max Activating Token Index: 880

Text #12

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.0696. Min Act: -0.1700

Data Index: 362142 (Open Web Text)

Max Activating Token Index: 26

Text #13

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.0571. Min Act: -0.1700

Data Index: 1461609 (Open Web Text)

Max Activating Token Index: 479

Text #14

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.0366. Min Act: -0.1700

Data Index: 5272655 (Open Web Text)

Max Activating Token Index: 594

Text #15

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.0589. Min Act: -0.1700

Data Index: 7950185 (Open Web Text)

Max Activating Token Index: 538

Text #16

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.0396. Min Act: -0.1700

Data Index: 7081806 (Open Web Text)

Max Activating Token Index: 471

Text #17

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.0359. Min Act: -0.1700

Data Index: 2081192 (Open Web Text)

Max Activating Token Index: 451

Text #18

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.0286. Min Act: -0.1700

Data Index: 1446997 (Open Web Text)

Max Activating Token Index: 743

Text #19

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.0318. Min Act: -0.1700

Data Index: 1987194 (Open Web Text)

Max Activating Token Index: 189