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

Dataset: Open Web Text

Neuron 64 in Layer 1

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: 1.8625. Min Range: -1.8625

Max Act: 1.8625. Min Act: -0.1700

Data Index: 7277907 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.8040. Min Act: -0.1700

Data Index: 3910786 (Open Web Text)

Max Activating Token Index: 29

Text #2

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7907. Min Act: -0.1700

Data Index: 5304794 (Open Web Text)

Max Activating Token Index: 943

Text #3

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7768. Min Act: -0.1700

Data Index: 4714175 (Open Web Text)

Max Activating Token Index: 255

Text #4

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7541. Min Act: -0.1700

Data Index: 4510650 (Open Web Text)

Max Activating Token Index: 48

Text #5

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7557. Min Act: -0.1700

Data Index: 4656653 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7432. Min Act: -0.1700

Data Index: 6488631 (Open Web Text)

Max Activating Token Index: 641

Text #7

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7353. Min Act: -0.1700

Data Index: 749294 (Open Web Text)

Max Activating Token Index: 248

Text #8

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7373. Min Act: -0.1700

Data Index: 2232360 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7398. Min Act: -0.1700

Data Index: 6820157 (Open Web Text)

Max Activating Token Index: 557

Text #10

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7301. Min Act: -0.1700

Data Index: 455060 (Open Web Text)

Max Activating Token Index: 338

Text #11

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7342. Min Act: -0.1700

Data Index: 1279947 (Open Web Text)

Max Activating Token Index: 782

Text #12

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7323. Min Act: -0.1700

Data Index: 1671073 (Open Web Text)

Max Activating Token Index: 188

Text #13

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7262. Min Act: -0.1700

Data Index: 4465654 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7390. Min Act: -0.1700

Data Index: 3687317 (Open Web Text)

Max Activating Token Index: 568

Text #15

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7237. Min Act: -0.1700

Data Index: 1337053 (Open Web Text)

Max Activating Token Index: 969

Text #16

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7208. Min Act: -0.1700

Data Index: 1673553 (Open Web Text)

Max Activating Token Index: 183

Text #17

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7241. Min Act: -0.1700

Data Index: 3005201 (Open Web Text)

Max Activating Token Index: 736

Text #18

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7182. Min Act: -0.1700

Data Index: 6799054 (Open Web Text)

Max Activating Token Index: 208

Text #19

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7158. Min Act: -0.1700

Data Index: 5462628 (Open Web Text)

Max Activating Token Index: 662