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

Dataset: Open Web Text

Neuron 445 in Layer 4

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: 5.8459. Min Range: -5.8459

Max Act: 5.8459. Min Act: -0.1700

Data Index: 7225734 (Open Web Text)

Max Activating Token Index: 261

Text #1

Max Range: 5.8459. Min Range: -5.8459

Max Act: 5.6149. Min Act: -0.1700

Data Index: 1904332 (Open Web Text)

Max Activating Token Index: 659

Text #2

Max Range: 5.8459. Min Range: -5.8459

Max Act: 5.4635. Min Act: -0.1700

Data Index: 1439947 (Open Web Text)

Max Activating Token Index: 948

Text #3

Max Range: 5.8459. Min Range: -5.8459

Max Act: 5.3771. Min Act: -0.1700

Data Index: 1955774 (Open Web Text)

Max Activating Token Index: 701

Text #4

Max Range: 5.8459. Min Range: -5.8459

Max Act: 5.4406. Min Act: -0.1700

Data Index: 7514818 (Open Web Text)

Max Activating Token Index: 481

Text #5

Max Range: 5.8459. Min Range: -5.8459

Max Act: 5.2875. Min Act: -0.1700

Data Index: 4688517 (Open Web Text)

Max Activating Token Index: 682

Text #6

Max Range: 5.8459. Min Range: -5.8459

Max Act: 5.4490. Min Act: -0.1700

Data Index: 2019418 (Open Web Text)

Max Activating Token Index: 973

Text #7

Max Range: 5.8459. Min Range: -5.8459

Max Act: 5.3394. Min Act: -0.1700

Data Index: 1656470 (Open Web Text)

Max Activating Token Index: 759

Text #8

Max Range: 5.8459. Min Range: -5.8459

Max Act: 5.3629. Min Act: -0.1700

Data Index: 3786930 (Open Web Text)

Max Activating Token Index: 422

Text #9

Max Range: 5.8459. Min Range: -5.8459

Max Act: 5.3458. Min Act: -0.1700

Data Index: 5267469 (Open Web Text)

Max Activating Token Index: 428

Text #10

Max Range: 5.8459. Min Range: -5.8459

Max Act: 5.2988. Min Act: -0.1700

Data Index: 1645159 (Open Web Text)

Max Activating Token Index: 400

Text #11

Max Range: 5.8459. Min Range: -5.8459

Max Act: 5.3267. Min Act: -0.1700

Data Index: 3385894 (Open Web Text)

Max Activating Token Index: 375

Text #12

Max Range: 5.8459. Min Range: -5.8459

Max Act: 5.3266. Min Act: -0.1700

Data Index: 528214 (Open Web Text)

Max Activating Token Index: 991

Text #13

Max Range: 5.8459. Min Range: -5.8459

Max Act: 5.2962. Min Act: -0.1700

Data Index: 1259512 (Open Web Text)

Max Activating Token Index: 184

Text #14

Max Range: 5.8459. Min Range: -5.8459

Max Act: 5.3545. Min Act: -0.1700

Data Index: 8620261 (Open Web Text)

Max Activating Token Index: 650

Text #15

Max Range: 5.8459. Min Range: -5.8459

Max Act: 5.2604. Min Act: -0.1700

Data Index: 3942701 (Open Web Text)

Max Activating Token Index: 388

Text #16

Max Range: 5.8459. Min Range: -5.8459

Max Act: 5.2230. Min Act: -0.1700

Data Index: 7263362 (Open Web Text)

Max Activating Token Index: 347

Text #17

Max Range: 5.8459. Min Range: -5.8459

Max Act: 5.2631. Min Act: -0.1700

Data Index: 4983855 (Open Web Text)

Max Activating Token Index: 561

Text #18

Max Range: 5.8459. Min Range: -5.8459

Max Act: 5.2225. Min Act: -0.1700

Data Index: 4356421 (Open Web Text)

Max Activating Token Index: 390

Text #19

Max Range: 5.8459. Min Range: -5.8459

Max Act: 5.2705. Min Act: -0.1700

Data Index: 5556298 (Open Web Text)

Max Activating Token Index: 274