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

Dataset: Open Web Text

Neuron 1725 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: 3.6457. Min Range: -3.6457

Max Act: 3.6457. Min Act: -0.1700

Data Index: 8660299 (Open Web Text)

Max Activating Token Index: 310

Text #1

Max Range: 3.6457. Min Range: -3.6457

Max Act: 3.6238. Min Act: -0.1700

Data Index: 3881474 (Open Web Text)

Max Activating Token Index: 433

Text #2

Max Range: 3.6457. Min Range: -3.6457

Max Act: 3.5755. Min Act: -0.1700

Data Index: 7521174 (Open Web Text)

Max Activating Token Index: 491

Text #3

Max Range: 3.6457. Min Range: -3.6457

Max Act: 3.5552. Min Act: -0.1700

Data Index: 6121062 (Open Web Text)

Max Activating Token Index: 59

Text #4

Max Range: 3.6457. Min Range: -3.6457

Max Act: 3.5642. Min Act: -0.1700

Data Index: 3324976 (Open Web Text)

Max Activating Token Index: 481

Text #5

Max Range: 3.6457. Min Range: -3.6457

Max Act: 3.5672. Min Act: -0.1700

Data Index: 7070895 (Open Web Text)

Max Activating Token Index: 506

Text #6

Max Range: 3.6457. Min Range: -3.6457

Max Act: 3.5411. Min Act: -0.1700

Data Index: 6005314 (Open Web Text)

Max Activating Token Index: 644

Text #7

Max Range: 3.6457. Min Range: -3.6457

Max Act: 3.5445. Min Act: -0.1700

Data Index: 2754981 (Open Web Text)

Max Activating Token Index: 619

Text #8

Max Range: 3.6457. Min Range: -3.6457

Max Act: 3.5481. Min Act: -0.1700

Data Index: 2695950 (Open Web Text)

Max Activating Token Index: 84

Text #9

Max Range: 3.6457. Min Range: -3.6457

Max Act: 3.5320. Min Act: -0.1700

Data Index: 5076047 (Open Web Text)

Max Activating Token Index: 597

Text #10

Max Range: 3.6457. Min Range: -3.6457

Max Act: 3.5503. Min Act: -0.1700

Data Index: 2368464 (Open Web Text)

Max Activating Token Index: 677

Text #11

Max Range: 3.6457. Min Range: -3.6457

Max Act: 3.5383. Min Act: -0.1700

Data Index: 6863559 (Open Web Text)

Max Activating Token Index: 139

Text #12

Max Range: 3.6457. Min Range: -3.6457

Max Act: 3.5386. Min Act: -0.1700

Data Index: 8311261 (Open Web Text)

Max Activating Token Index: 781

Text #13

Max Range: 3.6457. Min Range: -3.6457

Max Act: 3.5288. Min Act: -0.1700

Data Index: 8203996 (Open Web Text)

Max Activating Token Index: 86

Text #14

Max Range: 3.6457. Min Range: -3.6457

Max Act: 3.5283. Min Act: -0.1700

Data Index: 1798839 (Open Web Text)

Max Activating Token Index: 514

Text #15

Max Range: 3.6457. Min Range: -3.6457

Max Act: 3.5114. Min Act: -0.1700

Data Index: 6926065 (Open Web Text)

Max Activating Token Index: 214

Text #16

Max Range: 3.6457. Min Range: -3.6457

Max Act: 3.5055. Min Act: -0.1700

Data Index: 2381255 (Open Web Text)

Max Activating Token Index: 134

Text #17

Max Range: 3.6457. Min Range: -3.6457

Max Act: 3.4994. Min Act: -0.1700

Data Index: 3491397 (Open Web Text)

Max Activating Token Index: 59

Text #18

Max Range: 3.6457. Min Range: -3.6457

Max Act: 3.5076. Min Act: -0.1700

Data Index: 2856523 (Open Web Text)

Max Activating Token Index: 273

Text #19

Max Range: 3.6457. Min Range: -3.6457

Max Act: 3.4975. Min Act: -0.1700

Data Index: 2535963 (Open Web Text)

Max Activating Token Index: 829