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

Dataset: Open Web Text

Neuron 1278 in Layer 0

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: 0.8766. Min Range: -0.8766

Max Act: 0.8766. Min Act: -0.1480

Data Index: 8023175 (Open Web Text)

Max Activating Token Index: 1021

Text #1

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.7983. Min Act: -0.1520

Data Index: 1609534 (Open Web Text)

Max Activating Token Index: 1021

Text #2

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.7510. Min Act: -0.1524

Data Index: 316312 (Open Web Text)

Max Activating Token Index: 809

Text #3

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.7315. Min Act: -0.1530

Data Index: 5304010 (Open Web Text)

Max Activating Token Index: 843

Text #4

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.7290. Min Act: -0.1481

Data Index: 7408857 (Open Web Text)

Max Activating Token Index: 99

Text #5

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.7057. Min Act: -0.1379

Data Index: 3960758 (Open Web Text)

Max Activating Token Index: 813

Text #6

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.7058. Min Act: -0.1445

Data Index: 506508 (Open Web Text)

Max Activating Token Index: 227

Text #7

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6968. Min Act: -0.1513

Data Index: 442817 (Open Web Text)

Max Activating Token Index: 814

Text #8

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6946. Min Act: -0.1513

Data Index: 7571010 (Open Web Text)

Max Activating Token Index: 248

Text #9

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6961. Min Act: -0.1552

Data Index: 3166757 (Open Web Text)

Max Activating Token Index: 811

Text #10

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6904. Min Act: -0.1535

Data Index: 5513164 (Open Web Text)

Max Activating Token Index: 813

Text #11

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6928. Min Act: -0.1366

Data Index: 3743785 (Open Web Text)

Max Activating Token Index: 327

Text #12

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6921. Min Act: -0.1301

Data Index: 3712408 (Open Web Text)

Max Activating Token Index: 254

Text #13

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6865. Min Act: -0.1552

Data Index: 1943180 (Open Web Text)

Max Activating Token Index: 824

Text #14

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6899. Min Act: -0.1557

Data Index: 1397525 (Open Web Text)

Max Activating Token Index: 836

Text #15

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6893. Min Act: -0.1301

Data Index: 90315 (Open Web Text)

Max Activating Token Index: 855

Text #16

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6883. Min Act: -0.1552

Data Index: 6185470 (Open Web Text)

Max Activating Token Index: 848

Text #17

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6916. Min Act: -0.1503

Data Index: 8271017 (Open Web Text)

Max Activating Token Index: 793

Text #18

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6881. Min Act: -0.1379

Data Index: 1617089 (Open Web Text)

Max Activating Token Index: 806

Text #19

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6882. Min Act: -0.1614

Data Index: 3394721 (Open Web Text)

Max Activating Token Index: 814