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

Dataset: Open Web Text

Neuron 2913 in Layer 6

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: 5.5508. Min Range: -5.5508

Max Act: 5.5508. Min Act: -0.1700

Data Index: 6618087 (Open Web Text)

Max Activating Token Index: 862

Text #1

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.4536. Min Act: -0.1700

Data Index: 3186605 (Open Web Text)

Max Activating Token Index: 396

Text #2

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.4363. Min Act: -0.1700

Data Index: 1600988 (Open Web Text)

Max Activating Token Index: 875

Text #3

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.4304. Min Act: -0.1700

Data Index: 746335 (Open Web Text)

Max Activating Token Index: 648

Text #4

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.4418. Min Act: -0.1700

Data Index: 5683884 (Open Web Text)

Max Activating Token Index: 893

Text #5

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.3676. Min Act: -0.1700

Data Index: 4873015 (Open Web Text)

Max Activating Token Index: 999

Text #6

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.3776. Min Act: -0.1700

Data Index: 6784071 (Open Web Text)

Max Activating Token Index: 580

Text #7

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.3484. Min Act: -0.1700

Data Index: 1677033 (Open Web Text)

Max Activating Token Index: 335

Text #8

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.3504. Min Act: -0.1700

Data Index: 6193452 (Open Web Text)

Max Activating Token Index: 434

Text #9

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.3530. Min Act: -0.1700

Data Index: 7484547 (Open Web Text)

Max Activating Token Index: 694

Text #10

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.3460. Min Act: -0.1700

Data Index: 7368587 (Open Web Text)

Max Activating Token Index: 624

Text #11

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.3429. Min Act: -0.1700

Data Index: 6450091 (Open Web Text)

Max Activating Token Index: 900

Text #12

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.2692. Min Act: -0.1700

Data Index: 3888455 (Open Web Text)

Max Activating Token Index: 867

Text #13

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.3367. Min Act: -0.1700

Data Index: 7207493 (Open Web Text)

Max Activating Token Index: 571

Text #14

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.2869. Min Act: -0.1700

Data Index: 3412859 (Open Web Text)

Max Activating Token Index: 608

Text #15

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.3015. Min Act: -0.1700

Data Index: 3321223 (Open Web Text)

Max Activating Token Index: 981

Text #16

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.3129. Min Act: -0.1700

Data Index: 6985682 (Open Web Text)

Max Activating Token Index: 558

Text #17

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.3038. Min Act: -0.1700

Data Index: 6655252 (Open Web Text)

Max Activating Token Index: 689

Text #18

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.2474. Min Act: -0.1700

Data Index: 4708616 (Open Web Text)

Max Activating Token Index: 905

Text #19

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.2266. Min Act: -0.1700

Data Index: 3298700 (Open Web Text)

Max Activating Token Index: 935