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

Dataset: Open Web Text

Neuron 933 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: 5.7019. Min Range: -5.7019

Max Act: 5.7019. Min Act: -0.1700

Data Index: 6490634 (Open Web Text)

Max Activating Token Index: 179

Text #1

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.4367. Min Act: -0.1700

Data Index: 2234527 (Open Web Text)

Max Activating Token Index: 463

Text #2

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.3988. Min Act: -0.1700

Data Index: 1896510 (Open Web Text)

Max Activating Token Index: 470

Text #3

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.4376. Min Act: -0.1700

Data Index: 2971144 (Open Web Text)

Max Activating Token Index: 569

Text #4

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.3487. Min Act: -0.1700

Data Index: 3136485 (Open Web Text)

Max Activating Token Index: 509

Text #5

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.3912. Min Act: -0.1700

Data Index: 49656 (Open Web Text)

Max Activating Token Index: 375

Text #6

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.3815. Min Act: -0.1699

Data Index: 1087905 (Open Web Text)

Max Activating Token Index: 973

Text #7

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.3514. Min Act: -0.1700

Data Index: 5900813 (Open Web Text)

Max Activating Token Index: 438

Text #8

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.3966. Min Act: -0.1699

Data Index: 6716556 (Open Web Text)

Max Activating Token Index: 536

Text #9

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.3315. Min Act: -0.1700

Data Index: 6689964 (Open Web Text)

Max Activating Token Index: 337

Text #10

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.2770. Min Act: -0.1696

Data Index: 8311522 (Open Web Text)

Max Activating Token Index: 579

Text #11

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.2494. Min Act: -0.1700

Data Index: 5069464 (Open Web Text)

Max Activating Token Index: 423

Text #12

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.2473. Min Act: -0.1700

Data Index: 3458669 (Open Web Text)

Max Activating Token Index: 789

Text #13

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.2595. Min Act: -0.1699

Data Index: 6701287 (Open Web Text)

Max Activating Token Index: 689

Text #14

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.2777. Min Act: -0.1700

Data Index: 7672856 (Open Web Text)

Max Activating Token Index: 546

Text #15

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.2909. Min Act: -0.1699

Data Index: 6254289 (Open Web Text)

Max Activating Token Index: 595

Text #16

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.1780. Min Act: -0.1695

Data Index: 379448 (Open Web Text)

Max Activating Token Index: 372

Text #17

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.2311. Min Act: -0.1690

Data Index: 6782737 (Open Web Text)

Max Activating Token Index: 527

Text #18

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.1722. Min Act: -0.1699

Data Index: 474961 (Open Web Text)

Max Activating Token Index: 382

Text #19

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.2079. Min Act: -0.1700

Data Index: 1418264 (Open Web Text)

Max Activating Token Index: 199