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

Dataset: Open Web Text

Neuron 2800 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: 4.1431. Min Range: -4.1431

Max Act: 4.1431. Min Act: -0.1700

Data Index: 8384952 (Open Web Text)

Max Activating Token Index: 827

Text #1

Max Range: 4.1431. Min Range: -4.1431

Max Act: 4.0475. Min Act: -0.1700

Data Index: 7457204 (Open Web Text)

Max Activating Token Index: 331

Text #2

Max Range: 4.1431. Min Range: -4.1431

Max Act: 4.0438. Min Act: -0.1700

Data Index: 4723027 (Open Web Text)

Max Activating Token Index: 277

Text #3

Max Range: 4.1431. Min Range: -4.1431

Max Act: 4.0226. Min Act: -0.1700

Data Index: 786135 (Open Web Text)

Max Activating Token Index: 266

Text #4

Max Range: 4.1431. Min Range: -4.1431

Max Act: 4.0383. Min Act: -0.1700

Data Index: 2614231 (Open Web Text)

Max Activating Token Index: 511

Text #5

Max Range: 4.1431. Min Range: -4.1431

Max Act: 3.9773. Min Act: -0.1700

Data Index: 5534689 (Open Web Text)

Max Activating Token Index: 442

Text #6

Max Range: 4.1431. Min Range: -4.1431

Max Act: 3.9889. Min Act: -0.1700

Data Index: 914225 (Open Web Text)

Max Activating Token Index: 815

Text #7

Max Range: 4.1431. Min Range: -4.1431

Max Act: 3.9849. Min Act: -0.1700

Data Index: 4345415 (Open Web Text)

Max Activating Token Index: 775

Text #8

Max Range: 4.1431. Min Range: -4.1431

Max Act: 3.9561. Min Act: -0.1700

Data Index: 8020007 (Open Web Text)

Max Activating Token Index: 637

Text #9

Max Range: 4.1431. Min Range: -4.1431

Max Act: 3.9708. Min Act: -0.1700

Data Index: 3108845 (Open Web Text)

Max Activating Token Index: 576

Text #10

Max Range: 4.1431. Min Range: -4.1431

Max Act: 3.9491. Min Act: -0.1700

Data Index: 8412906 (Open Web Text)

Max Activating Token Index: 734

Text #11

Max Range: 4.1431. Min Range: -4.1431

Max Act: 3.9268. Min Act: -0.1700

Data Index: 2637929 (Open Web Text)

Max Activating Token Index: 302

Text #12

Max Range: 4.1431. Min Range: -4.1431

Max Act: 3.9360. Min Act: -0.1700

Data Index: 6483148 (Open Web Text)

Max Activating Token Index: 901

Text #13

Max Range: 4.1431. Min Range: -4.1431

Max Act: 3.9496. Min Act: -0.1700

Data Index: 4921843 (Open Web Text)

Max Activating Token Index: 961

Text #14

Max Range: 4.1431. Min Range: -4.1431

Max Act: 3.9629. Min Act: -0.1700

Data Index: 6256680 (Open Web Text)

Max Activating Token Index: 292

Text #15

Max Range: 4.1431. Min Range: -4.1431

Max Act: 3.8993. Min Act: -0.1700

Data Index: 4749189 (Open Web Text)

Max Activating Token Index: 133

Text #16

Max Range: 4.1431. Min Range: -4.1431

Max Act: 3.9285. Min Act: -0.1700

Data Index: 1385331 (Open Web Text)

Max Activating Token Index: 538

Text #17

Max Range: 4.1431. Min Range: -4.1431

Max Act: 3.9267. Min Act: -0.1700

Data Index: 1692597 (Open Web Text)

Max Activating Token Index: 604

Text #18

Max Range: 4.1431. Min Range: -4.1431

Max Act: 3.9243. Min Act: -0.1700

Data Index: 6891449 (Open Web Text)

Max Activating Token Index: 284

Text #19

Max Range: 4.1431. Min Range: -4.1431

Max Act: 3.8829. Min Act: -0.1700

Data Index: 6980755 (Open Web Text)

Max Activating Token Index: 430