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

Dataset: Open Web Text

Neuron 1086 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: 1.5309. Min Range: -1.5309

Max Act: 1.5309. Min Act: -0.1562

Data Index: 5272656 (Open Web Text)

Max Activating Token Index: 375

Text #1

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.4930. Min Act: -0.1650

Data Index: 6965520 (Open Web Text)

Max Activating Token Index: 422

Text #2

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.5031. Min Act: -0.1580

Data Index: 3473474 (Open Web Text)

Max Activating Token Index: 484

Text #3

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.4936. Min Act: -0.1574

Data Index: 5237226 (Open Web Text)

Max Activating Token Index: 420

Text #4

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.4947. Min Act: -0.1613

Data Index: 6818761 (Open Web Text)

Max Activating Token Index: 549

Text #5

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.4907. Min Act: -0.1355

Data Index: 7332769 (Open Web Text)

Max Activating Token Index: 626

Text #6

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.4794. Min Act: -0.1676

Data Index: 7517482 (Open Web Text)

Max Activating Token Index: 908

Text #7

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.4784. Min Act: -0.1661

Data Index: 4305377 (Open Web Text)

Max Activating Token Index: 828

Text #8

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.4822. Min Act: -0.1695

Data Index: 7078284 (Open Web Text)

Max Activating Token Index: 399

Text #9

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.4729. Min Act: -0.1488

Data Index: 3924918 (Open Web Text)

Max Activating Token Index: 400

Text #10

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.4713. Min Act: -0.1700

Data Index: 5021015 (Open Web Text)

Max Activating Token Index: 491

Text #11

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.4718. Min Act: -0.1688

Data Index: 8217422 (Open Web Text)

Max Activating Token Index: 309

Text #12

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.4674. Min Act: -0.1684

Data Index: 5794018 (Open Web Text)

Max Activating Token Index: 679

Text #13

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.4581. Min Act: -0.1696

Data Index: 2266478 (Open Web Text)

Max Activating Token Index: 814

Text #14

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.4547. Min Act: -0.1259

Data Index: 6761472 (Open Web Text)

Max Activating Token Index: 435

Text #15

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.4503. Min Act: -0.1697

Data Index: 3896901 (Open Web Text)

Max Activating Token Index: 635

Text #16

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.4591. Min Act: -0.1650

Data Index: 5750672 (Open Web Text)

Max Activating Token Index: 357

Text #17

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.4477. Min Act: -0.1691

Data Index: 381662 (Open Web Text)

Max Activating Token Index: 258

Text #18

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.4432. Min Act: -0.1659

Data Index: 7438290 (Open Web Text)

Max Activating Token Index: 546

Text #19

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.4445. Min Act: -0.1594

Data Index: 5492348 (Open Web Text)

Max Activating Token Index: 724