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

Dataset: Open Web Text

Neuron 1792 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: 3.0310. Min Range: -3.0310

Max Act: 3.0310. Min Act: -0.1700

Data Index: 1319073 (Open Web Text)

Max Activating Token Index: 423

Text #1

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9297. Min Act: -0.1700

Data Index: 1606073 (Open Web Text)

Max Activating Token Index: 878

Text #2

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9123. Min Act: -0.1700

Data Index: 2049950 (Open Web Text)

Max Activating Token Index: 663

Text #3

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9347. Min Act: -0.1700

Data Index: 4549866 (Open Web Text)

Max Activating Token Index: 640

Text #4

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9030. Min Act: -0.1700

Data Index: 4813247 (Open Web Text)

Max Activating Token Index: 425

Text #5

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.8606. Min Act: -0.1700

Data Index: 481592 (Open Web Text)

Max Activating Token Index: 337

Text #6

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.8302. Min Act: -0.1700

Data Index: 8411788 (Open Web Text)

Max Activating Token Index: 857

Text #7

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.8044. Min Act: -0.1700

Data Index: 306903 (Open Web Text)

Max Activating Token Index: 433

Text #8

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.7830. Min Act: -0.1700

Data Index: 6039796 (Open Web Text)

Max Activating Token Index: 823

Text #9

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.7762. Min Act: -0.1700

Data Index: 8821172 (Open Web Text)

Max Activating Token Index: 808

Text #10

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.7918. Min Act: -0.1700

Data Index: 8745268 (Open Web Text)

Max Activating Token Index: 33

Text #11

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.7668. Min Act: -0.1700

Data Index: 3000030 (Open Web Text)

Max Activating Token Index: 766

Text #12

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.7007. Min Act: -0.1700

Data Index: 6527272 (Open Web Text)

Max Activating Token Index: 391

Text #13

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.7265. Min Act: -0.1700

Data Index: 5430870 (Open Web Text)

Max Activating Token Index: 867

Text #14

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.7406. Min Act: -0.1700

Data Index: 3264818 (Open Web Text)

Max Activating Token Index: 79

Text #15

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.6962. Min Act: -0.1700

Data Index: 3583112 (Open Web Text)

Max Activating Token Index: 331

Text #16

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.6895. Min Act: -0.1700

Data Index: 1373720 (Open Web Text)

Max Activating Token Index: 1008

Text #17

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.6780. Min Act: -0.1700

Data Index: 4453618 (Open Web Text)

Max Activating Token Index: 733

Text #18

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.7130. Min Act: -0.1700

Data Index: 3202715 (Open Web Text)

Max Activating Token Index: 1016

Text #19

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.6869. Min Act: -0.1700

Data Index: 4166759 (Open Web Text)

Max Activating Token Index: 829