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

Dataset: Open Web Text

Neuron 1444 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: 4.4415. Min Range: -4.4415

Max Act: 4.4415. Min Act: -0.1700

Data Index: 2526975 (Open Web Text)

Max Activating Token Index: 1000

Text #1

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3863. Min Act: -0.1700

Data Index: 5433900 (Open Web Text)

Max Activating Token Index: 568

Text #2

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3710. Min Act: -0.1700

Data Index: 3584704 (Open Web Text)

Max Activating Token Index: 463

Text #3

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3737. Min Act: -0.1700

Data Index: 7402650 (Open Web Text)

Max Activating Token Index: 160

Text #4

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3852. Min Act: -0.1700

Data Index: 2236763 (Open Web Text)

Max Activating Token Index: 400

Text #5

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3794. Min Act: -0.1700

Data Index: 2462058 (Open Web Text)

Max Activating Token Index: 576

Text #6

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3414. Min Act: -0.1700

Data Index: 5120956 (Open Web Text)

Max Activating Token Index: 159

Text #7

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3318. Min Act: -0.1700

Data Index: 290275 (Open Web Text)

Max Activating Token Index: 621

Text #8

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3287. Min Act: -0.1700

Data Index: 4830724 (Open Web Text)

Max Activating Token Index: 568

Text #9

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3387. Min Act: -0.1700

Data Index: 1321036 (Open Web Text)

Max Activating Token Index: 437

Text #10

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3224. Min Act: -0.1700

Data Index: 4314178 (Open Web Text)

Max Activating Token Index: 569

Text #11

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3325. Min Act: -0.1700

Data Index: 2640876 (Open Web Text)

Max Activating Token Index: 320

Text #12

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3435. Min Act: -0.1700

Data Index: 7607853 (Open Web Text)

Max Activating Token Index: 160

Text #13

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3518. Min Act: -0.1700

Data Index: 3756564 (Open Web Text)

Max Activating Token Index: 508

Text #14

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3365. Min Act: -0.1700

Data Index: 7233699 (Open Web Text)

Max Activating Token Index: 545

Text #15

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3320. Min Act: -0.1700

Data Index: 6037392 (Open Web Text)

Max Activating Token Index: 586

Text #16

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3383. Min Act: -0.1700

Data Index: 5915075 (Open Web Text)

Max Activating Token Index: 107

Text #17

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3010. Min Act: -0.1700

Data Index: 4723254 (Open Web Text)

Max Activating Token Index: 376

Text #18

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3228. Min Act: -0.1700

Data Index: 4913848 (Open Web Text)

Max Activating Token Index: 381

Text #19

Max Range: 4.4415. Min Range: -4.4415

Max Act: 4.3144. Min Act: -0.1700

Data Index: 710419 (Open Web Text)

Max Activating Token Index: 428