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

Dataset: Open Web Text

Neuron 2650 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: 1.5412. Min Range: -1.5412

Max Act: 1.5412. Min Act: -0.1698

Data Index: 3805325 (Open Web Text)

Max Activating Token Index: 340

Text #1

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.5137. Min Act: -0.1700

Data Index: 8677906 (Open Web Text)

Max Activating Token Index: 482

Text #2

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.4975. Min Act: -0.1700

Data Index: 716293 (Open Web Text)

Max Activating Token Index: 240

Text #3

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.5006. Min Act: -0.1651

Data Index: 2322020 (Open Web Text)

Max Activating Token Index: 416

Text #4

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.5070. Min Act: -0.1678

Data Index: 5550589 (Open Web Text)

Max Activating Token Index: 136

Text #5

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.5050. Min Act: -0.1700

Data Index: 1807854 (Open Web Text)

Max Activating Token Index: 959

Text #6

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.4924. Min Act: -0.1700

Data Index: 1716997 (Open Web Text)

Max Activating Token Index: 802

Text #7

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.4643. Min Act: -0.1700

Data Index: 2190737 (Open Web Text)

Max Activating Token Index: 461

Text #8

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.4680. Min Act: -0.1700

Data Index: 2756883 (Open Web Text)

Max Activating Token Index: 398

Text #9

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.4711. Min Act: -0.1697

Data Index: 6943499 (Open Web Text)

Max Activating Token Index: 583

Text #10

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.4688. Min Act: -0.1700

Data Index: 146456 (Open Web Text)

Max Activating Token Index: 913

Text #11

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.4693. Min Act: -0.1699

Data Index: 8443285 (Open Web Text)

Max Activating Token Index: 369

Text #12

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.4609. Min Act: -0.1700

Data Index: 6236531 (Open Web Text)

Max Activating Token Index: 631

Text #13

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.4624. Min Act: -0.1699

Data Index: 6051699 (Open Web Text)

Max Activating Token Index: 540

Text #14

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.4599. Min Act: -0.1700

Data Index: 3852673 (Open Web Text)

Max Activating Token Index: 633

Text #15

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.4606. Min Act: -0.1700

Data Index: 2019078 (Open Web Text)

Max Activating Token Index: 410

Text #16

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.4660. Min Act: -0.1698

Data Index: 3674858 (Open Web Text)

Max Activating Token Index: 525

Text #17

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.4647. Min Act: -0.1700

Data Index: 1785564 (Open Web Text)

Max Activating Token Index: 975

Text #18

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.4603. Min Act: -0.1700

Data Index: 3004239 (Open Web Text)

Max Activating Token Index: 534

Text #19

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.4535. Min Act: -0.1697

Data Index: 585759 (Open Web Text)

Max Activating Token Index: 587