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

Dataset: Open Web Text

Neuron 1224 in Layer 6

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: 4.4317. Min Range: -4.4317

Max Act: 4.4274. Min Act: -0.1700

Data Index: 3600600 (Open Web Text)

Max Activating Token Index: 960

Text #1

Max Range: 4.4317. Min Range: -4.4317

Max Act: 4.4317. Min Act: -0.1700

Data Index: 3738161 (Open Web Text)

Max Activating Token Index: 269

Text #2

Max Range: 4.4317. Min Range: -4.4317

Max Act: 4.3028. Min Act: -0.1700

Data Index: 6483417 (Open Web Text)

Max Activating Token Index: 643

Text #3

Max Range: 4.4317. Min Range: -4.4317

Max Act: 4.2908. Min Act: -0.1700

Data Index: 1854484 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 4.4317. Min Range: -4.4317

Max Act: 4.2941. Min Act: -0.1700

Data Index: 3024298 (Open Web Text)

Max Activating Token Index: 667

Text #5

Max Range: 4.4317. Min Range: -4.4317

Max Act: 4.2479. Min Act: -0.1700

Data Index: 6446621 (Open Web Text)

Max Activating Token Index: 158

Text #6

Max Range: 4.4317. Min Range: -4.4317

Max Act: 4.1971. Min Act: -0.1700

Data Index: 2973646 (Open Web Text)

Max Activating Token Index: 862

Text #7

Max Range: 4.4317. Min Range: -4.4317

Max Act: 4.2045. Min Act: -0.1700

Data Index: 6352639 (Open Web Text)

Max Activating Token Index: 651

Text #8

Max Range: 4.4317. Min Range: -4.4317

Max Act: 4.1763. Min Act: -0.1700

Data Index: 654394 (Open Web Text)

Max Activating Token Index: 544

Text #9

Max Range: 4.4317. Min Range: -4.4317

Max Act: 4.1635. Min Act: -0.1700

Data Index: 3698311 (Open Web Text)

Max Activating Token Index: 843

Text #10

Max Range: 4.4317. Min Range: -4.4317

Max Act: 4.1527. Min Act: -0.1700

Data Index: 3935141 (Open Web Text)

Max Activating Token Index: 588

Text #11

Max Range: 4.4317. Min Range: -4.4317

Max Act: 4.1564. Min Act: -0.1700

Data Index: 4668292 (Open Web Text)

Max Activating Token Index: 494

Text #12

Max Range: 4.4317. Min Range: -4.4317

Max Act: 4.1590. Min Act: -0.1700

Data Index: 4961097 (Open Web Text)

Max Activating Token Index: 210

Text #13

Max Range: 4.4317. Min Range: -4.4317

Max Act: 4.1571. Min Act: -0.1700

Data Index: 1027172 (Open Web Text)

Max Activating Token Index: 323

Text #14

Max Range: 4.4317. Min Range: -4.4317

Max Act: 4.1822. Min Act: -0.1700

Data Index: 53626 (Open Web Text)

Max Activating Token Index: 477

Text #15

Max Range: 4.4317. Min Range: -4.4317

Max Act: 4.1239. Min Act: -0.1700

Data Index: 4494367 (Open Web Text)

Max Activating Token Index: 459

Text #16

Max Range: 4.4317. Min Range: -4.4317

Max Act: 4.1426. Min Act: -0.1700

Data Index: 1299575 (Open Web Text)

Max Activating Token Index: 970

Text #17

Max Range: 4.4317. Min Range: -4.4317

Max Act: 4.1138. Min Act: -0.1700

Data Index: 4609486 (Open Web Text)

Max Activating Token Index: 824

Text #18

Max Range: 4.4317. Min Range: -4.4317

Max Act: 4.1436. Min Act: -0.1700

Data Index: 5422804 (Open Web Text)

Max Activating Token Index: 947

Text #19

Max Range: 4.4317. Min Range: -4.4317

Max Act: 4.1367. Min Act: -0.1700

Data Index: 6388975 (Open Web Text)

Max Activating Token Index: 469