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

Dataset: Open Web Text

Neuron 280 in Layer 0

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: 1.3363. Min Range: -1.3363

Max Act: 1.3363. Min Act: -0.1700

Data Index: 717713 (Open Web Text)

Max Activating Token Index: 630

Text #1

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.3238. Min Act: -0.1700

Data Index: 8156035 (Open Web Text)

Max Activating Token Index: 661

Text #2

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2827. Min Act: -0.1700

Data Index: 1481231 (Open Web Text)

Max Activating Token Index: 655

Text #3

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2727. Min Act: -0.1700

Data Index: 489034 (Open Web Text)

Max Activating Token Index: 652

Text #4

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2911. Min Act: -0.1697

Data Index: 2808148 (Open Web Text)

Max Activating Token Index: 642

Text #5

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2585. Min Act: -0.1698

Data Index: 8005824 (Open Web Text)

Max Activating Token Index: 644

Text #6

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2532. Min Act: -0.1700

Data Index: 3973591 (Open Web Text)

Max Activating Token Index: 652

Text #7

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2641. Min Act: -0.1700

Data Index: 3785225 (Open Web Text)

Max Activating Token Index: 645

Text #8

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2536. Min Act: -0.1700

Data Index: 8152587 (Open Web Text)

Max Activating Token Index: 638

Text #9

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2542. Min Act: -0.1700

Data Index: 4536546 (Open Web Text)

Max Activating Token Index: 614

Text #10

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2629. Min Act: -0.1700

Data Index: 2488899 (Open Web Text)

Max Activating Token Index: 629

Text #11

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2542. Min Act: -0.1700

Data Index: 2467589 (Open Web Text)

Max Activating Token Index: 649

Text #12

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2515. Min Act: -0.1700

Data Index: 43720 (Open Web Text)

Max Activating Token Index: 654

Text #13

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2521. Min Act: -0.1700

Data Index: 6412423 (Open Web Text)

Max Activating Token Index: 605

Text #14

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2512. Min Act: -0.1700

Data Index: 785065 (Open Web Text)

Max Activating Token Index: 621

Text #15

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2519. Min Act: -0.1700

Data Index: 6258519 (Open Web Text)

Max Activating Token Index: 639

Text #16

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2448. Min Act: -0.1700

Data Index: 5443296 (Open Web Text)

Max Activating Token Index: 645

Text #17

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2389. Min Act: -0.1700

Data Index: 2669057 (Open Web Text)

Max Activating Token Index: 659

Text #18

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2415. Min Act: -0.1700

Data Index: 3496651 (Open Web Text)

Max Activating Token Index: 632

Text #19

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2372. Min Act: -0.1700

Data Index: 3498301 (Open Web Text)

Max Activating Token Index: 635