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

Dataset: Open Web Text

Neuron 1820 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: 5.7864. Min Range: -5.7864

Max Act: 5.7864. Min Act: -0.1700

Data Index: 2851833 (Open Web Text)

Max Activating Token Index: 731

Text #1

Max Range: 5.7864. Min Range: -5.7864

Max Act: 5.6690. Min Act: -0.1700

Data Index: 3283747 (Open Web Text)

Max Activating Token Index: 656

Text #2

Max Range: 5.7864. Min Range: -5.7864

Max Act: 5.6691. Min Act: -0.1700

Data Index: 8311439 (Open Web Text)

Max Activating Token Index: 534

Text #3

Max Range: 5.7864. Min Range: -5.7864

Max Act: 5.5088. Min Act: -0.1700

Data Index: 4778251 (Open Web Text)

Max Activating Token Index: 326

Text #4

Max Range: 5.7864. Min Range: -5.7864

Max Act: 5.5285. Min Act: -0.1700

Data Index: 4706553 (Open Web Text)

Max Activating Token Index: 448

Text #5

Max Range: 5.7864. Min Range: -5.7864

Max Act: 5.4076. Min Act: -0.1700

Data Index: 1550936 (Open Web Text)

Max Activating Token Index: 931

Text #6

Max Range: 5.7864. Min Range: -5.7864

Max Act: 5.4175. Min Act: -0.1700

Data Index: 8490276 (Open Web Text)

Max Activating Token Index: 818

Text #7

Max Range: 5.7864. Min Range: -5.7864

Max Act: 5.3801. Min Act: -0.1700

Data Index: 745723 (Open Web Text)

Max Activating Token Index: 252

Text #8

Max Range: 5.7864. Min Range: -5.7864

Max Act: 5.3106. Min Act: -0.1700

Data Index: 5833890 (Open Web Text)

Max Activating Token Index: 437

Text #9

Max Range: 5.7864. Min Range: -5.7864

Max Act: 5.3571. Min Act: -0.1700

Data Index: 4458502 (Open Web Text)

Max Activating Token Index: 430

Text #10

Max Range: 5.7864. Min Range: -5.7864

Max Act: 5.3351. Min Act: -0.1700

Data Index: 7640444 (Open Web Text)

Max Activating Token Index: 983

Text #11

Max Range: 5.7864. Min Range: -5.7864

Max Act: 5.3341. Min Act: -0.1700

Data Index: 4645614 (Open Web Text)

Max Activating Token Index: 306

Text #12

Max Range: 5.7864. Min Range: -5.7864

Max Act: 5.3286. Min Act: -0.1700

Data Index: 7529483 (Open Web Text)

Max Activating Token Index: 241

Text #13

Max Range: 5.7864. Min Range: -5.7864

Max Act: 5.2618. Min Act: -0.1700

Data Index: 1241287 (Open Web Text)

Max Activating Token Index: 74

Text #14

Max Range: 5.7864. Min Range: -5.7864

Max Act: 5.2744. Min Act: -0.1700

Data Index: 5102761 (Open Web Text)

Max Activating Token Index: 350

Text #15

Max Range: 5.7864. Min Range: -5.7864

Max Act: 5.2733. Min Act: -0.1700

Data Index: 7472616 (Open Web Text)

Max Activating Token Index: 934

Text #16

Max Range: 5.7864. Min Range: -5.7864

Max Act: 5.2830. Min Act: -0.1700

Data Index: 1528263 (Open Web Text)

Max Activating Token Index: 736

Text #17

Max Range: 5.7864. Min Range: -5.7864

Max Act: 5.2405. Min Act: -0.1700

Data Index: 6519473 (Open Web Text)

Max Activating Token Index: 462

Text #18

Max Range: 5.7864. Min Range: -5.7864

Max Act: 5.2149. Min Act: -0.1700

Data Index: 51624 (Open Web Text)

Max Activating Token Index: 139

Text #19

Max Range: 5.7864. Min Range: -5.7864

Max Act: 5.2547. Min Act: -0.1700

Data Index: 3650598 (Open Web Text)

Max Activating Token Index: 327