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

Dataset: Open Web Text

Neuron 648 in Layer 3

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: 4.8834. Min Range: -4.8834

Max Act: 4.8495. Min Act: -0.1700

Data Index: 4142572 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 4.8834. Min Range: -4.8834

Max Act: 4.8834. Min Act: -0.1700

Data Index: 949097 (Open Web Text)

Max Activating Token Index: 615

Text #2

Max Range: 4.8834. Min Range: -4.8834

Max Act: 4.8082. Min Act: -0.1700

Data Index: 3343660 (Open Web Text)

Max Activating Token Index: 598

Text #3

Max Range: 4.8834. Min Range: -4.8834

Max Act: 4.8120. Min Act: -0.1700

Data Index: 2091097 (Open Web Text)

Max Activating Token Index: 787

Text #4

Max Range: 4.8834. Min Range: -4.8834

Max Act: 4.7311. Min Act: -0.1700

Data Index: 8629450 (Open Web Text)

Max Activating Token Index: 669

Text #5

Max Range: 4.8834. Min Range: -4.8834

Max Act: 4.7510. Min Act: -0.1698

Data Index: 4142571 (Open Web Text)

Max Activating Token Index: 677

Text #6

Max Range: 4.8834. Min Range: -4.8834

Max Act: 4.7081. Min Act: -0.1697

Data Index: 6592524 (Open Web Text)

Max Activating Token Index: 612

Text #7

Max Range: 4.8834. Min Range: -4.8834

Max Act: 4.7002. Min Act: -0.1700

Data Index: 1864190 (Open Web Text)

Max Activating Token Index: 859

Text #8

Max Range: 4.8834. Min Range: -4.8834

Max Act: 4.7107. Min Act: -0.1700

Data Index: 2517746 (Open Web Text)

Max Activating Token Index: 418

Text #9

Max Range: 4.8834. Min Range: -4.8834

Max Act: 4.6212. Min Act: -0.1700

Data Index: 6095439 (Open Web Text)

Max Activating Token Index: 604

Text #10

Max Range: 4.8834. Min Range: -4.8834

Max Act: 4.6556. Min Act: -0.1700

Data Index: 4819017 (Open Web Text)

Max Activating Token Index: 417

Text #11

Max Range: 4.8834. Min Range: -4.8834

Max Act: 4.7330. Min Act: -0.1700

Data Index: 7833948 (Open Web Text)

Max Activating Token Index: 625

Text #12

Max Range: 4.8834. Min Range: -4.8834

Max Act: 4.6099. Min Act: -0.1699

Data Index: 6896652 (Open Web Text)

Max Activating Token Index: 500

Text #13

Max Range: 4.8834. Min Range: -4.8834

Max Act: 4.6342. Min Act: -0.1700

Data Index: 710741 (Open Web Text)

Max Activating Token Index: 422

Text #14

Max Range: 4.8834. Min Range: -4.8834

Max Act: 4.6111. Min Act: -0.1697

Data Index: 7316326 (Open Web Text)

Max Activating Token Index: 357

Text #15

Max Range: 4.8834. Min Range: -4.8834

Max Act: 4.6493. Min Act: -0.1700

Data Index: 3202254 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 4.8834. Min Range: -4.8834

Max Act: 4.6494. Min Act: -0.1699

Data Index: 2241854 (Open Web Text)

Max Activating Token Index: 827

Text #17

Max Range: 4.8834. Min Range: -4.8834

Max Act: 4.6041. Min Act: -0.1700

Data Index: 5776632 (Open Web Text)

Max Activating Token Index: 413

Text #18

Max Range: 4.8834. Min Range: -4.8834

Max Act: 4.6267. Min Act: -0.1700

Data Index: 5730819 (Open Web Text)

Max Activating Token Index: 80

Text #19

Max Range: 4.8834. Min Range: -4.8834

Max Act: 4.6347. Min Act: -0.1700

Data Index: 14634 (Open Web Text)

Max Activating Token Index: 594