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

Dataset: Open Web Text

Neuron 423 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: 4.8307. Min Range: -4.8307

Max Act: 4.8307. Min Act: -0.1700

Data Index: 1289390 (Open Web Text)

Max Activating Token Index: 885

Text #1

Max Range: 4.8307. Min Range: -4.8307

Max Act: 4.7927. Min Act: -0.1700

Data Index: 7447266 (Open Web Text)

Max Activating Token Index: 223

Text #2

Max Range: 4.8307. Min Range: -4.8307

Max Act: 4.7581. Min Act: -0.1700

Data Index: 813640 (Open Web Text)

Max Activating Token Index: 268

Text #3

Max Range: 4.8307. Min Range: -4.8307

Max Act: 4.7737. Min Act: -0.1700

Data Index: 6049388 (Open Web Text)

Max Activating Token Index: 198

Text #4

Max Range: 4.8307. Min Range: -4.8307

Max Act: 4.7043. Min Act: -0.1700

Data Index: 523315 (Open Web Text)

Max Activating Token Index: 489

Text #5

Max Range: 4.8307. Min Range: -4.8307

Max Act: 4.6368. Min Act: -0.1700

Data Index: 7128993 (Open Web Text)

Max Activating Token Index: 881

Text #6

Max Range: 4.8307. Min Range: -4.8307

Max Act: 4.6751. Min Act: -0.1700

Data Index: 4892707 (Open Web Text)

Max Activating Token Index: 923

Text #7

Max Range: 4.8307. Min Range: -4.8307

Max Act: 4.6923. Min Act: -0.1700

Data Index: 4669108 (Open Web Text)

Max Activating Token Index: 962

Text #8

Max Range: 4.8307. Min Range: -4.8307

Max Act: 4.6276. Min Act: -0.1700

Data Index: 2191498 (Open Web Text)

Max Activating Token Index: 894

Text #9

Max Range: 4.8307. Min Range: -4.8307

Max Act: 4.5452. Min Act: -0.1700

Data Index: 6464864 (Open Web Text)

Max Activating Token Index: 565

Text #10

Max Range: 4.8307. Min Range: -4.8307

Max Act: 4.6455. Min Act: -0.1700

Data Index: 2850441 (Open Web Text)

Max Activating Token Index: 862

Text #11

Max Range: 4.8307. Min Range: -4.8307

Max Act: 4.5732. Min Act: -0.1700

Data Index: 6594725 (Open Web Text)

Max Activating Token Index: 668

Text #12

Max Range: 4.8307. Min Range: -4.8307

Max Act: 4.5696. Min Act: -0.1700

Data Index: 3494744 (Open Web Text)

Max Activating Token Index: 402

Text #13

Max Range: 4.8307. Min Range: -4.8307

Max Act: 4.5639. Min Act: -0.1700

Data Index: 4161422 (Open Web Text)

Max Activating Token Index: 474

Text #14

Max Range: 4.8307. Min Range: -4.8307

Max Act: 4.5759. Min Act: -0.1700

Data Index: 1765356 (Open Web Text)

Max Activating Token Index: 224

Text #15

Max Range: 4.8307. Min Range: -4.8307

Max Act: 4.5947. Min Act: -0.1700

Data Index: 6825788 (Open Web Text)

Max Activating Token Index: 44

Text #16

Max Range: 4.8307. Min Range: -4.8307

Max Act: 4.5294. Min Act: -0.1700

Data Index: 4330775 (Open Web Text)

Max Activating Token Index: 599

Text #17

Max Range: 4.8307. Min Range: -4.8307

Max Act: 4.5638. Min Act: -0.1700

Data Index: 7111848 (Open Web Text)

Max Activating Token Index: 525

Text #18

Max Range: 4.8307. Min Range: -4.8307

Max Act: 4.5033. Min Act: -0.1700

Data Index: 5202230 (Open Web Text)

Max Activating Token Index: 735

Text #19

Max Range: 4.8307. Min Range: -4.8307

Max Act: 4.5435. Min Act: -0.1700

Data Index: 1479428 (Open Web Text)

Max Activating Token Index: 272