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

Dataset: Open Web Text

Neuron 2375 in Layer 3

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: 1.8549. Min Range: -1.8549

Max Act: 1.8549. Min Act: -0.1526

Data Index: 4339758 (Open Web Text)

Max Activating Token Index: 400

Text #1

Max Range: 1.8549. Min Range: -1.8549

Max Act: 1.8330. Min Act: -0.1640

Data Index: 8338400 (Open Web Text)

Max Activating Token Index: 704

Text #2

Max Range: 1.8549. Min Range: -1.8549

Max Act: 1.8198. Min Act: -0.1573

Data Index: 3495537 (Open Web Text)

Max Activating Token Index: 542

Text #3

Max Range: 1.8549. Min Range: -1.8549

Max Act: 1.8124. Min Act: -0.1573

Data Index: 6719783 (Open Web Text)

Max Activating Token Index: 636

Text #4

Max Range: 1.8549. Min Range: -1.8549

Max Act: 1.8031. Min Act: -0.0988

Data Index: 3513885 (Open Web Text)

Max Activating Token Index: 699

Text #5

Max Range: 1.8549. Min Range: -1.8549

Max Act: 1.8051. Min Act: -0.1374

Data Index: 8746634 (Open Web Text)

Max Activating Token Index: 674

Text #6

Max Range: 1.8549. Min Range: -1.8549

Max Act: 1.7931. Min Act: -0.1428

Data Index: 7773450 (Open Web Text)

Max Activating Token Index: 624

Text #7

Max Range: 1.8549. Min Range: -1.8549

Max Act: 1.7902. Min Act: -0.1469

Data Index: 7922417 (Open Web Text)

Max Activating Token Index: 667

Text #8

Max Range: 1.8549. Min Range: -1.8549

Max Act: 1.7844. Min Act: -0.1649

Data Index: 7570792 (Open Web Text)

Max Activating Token Index: 616

Text #9

Max Range: 1.8549. Min Range: -1.8549

Max Act: 1.7810. Min Act: -0.1555

Data Index: 4293289 (Open Web Text)

Max Activating Token Index: 601

Text #10

Max Range: 1.8549. Min Range: -1.8549

Max Act: 1.7720. Min Act: -0.1698

Data Index: 2784463 (Open Web Text)

Max Activating Token Index: 729

Text #11

Max Range: 1.8549. Min Range: -1.8549

Max Act: 1.7826. Min Act: -0.1375

Data Index: 5703382 (Open Web Text)

Max Activating Token Index: 687

Text #12

Max Range: 1.8549. Min Range: -1.8549

Max Act: 1.7594. Min Act: -0.1054

Data Index: 8746636 (Open Web Text)

Max Activating Token Index: 732

Text #13

Max Range: 1.8549. Min Range: -1.8549

Max Act: 1.7621. Min Act: -0.1605

Data Index: 6078707 (Open Web Text)

Max Activating Token Index: 581

Text #14

Max Range: 1.8549. Min Range: -1.8549

Max Act: 1.7538. Min Act: -0.1223

Data Index: 8746635 (Open Web Text)

Max Activating Token Index: 697

Text #15

Max Range: 1.8549. Min Range: -1.8549

Max Act: 1.7576. Min Act: -0.1634

Data Index: 4826076 (Open Web Text)

Max Activating Token Index: 447

Text #16

Max Range: 1.8549. Min Range: -1.8549

Max Act: 1.7373. Min Act: -0.1512

Data Index: 8332161 (Open Web Text)

Max Activating Token Index: 775

Text #17

Max Range: 1.8549. Min Range: -1.8549

Max Act: 1.7542. Min Act: -0.1641

Data Index: 514820 (Open Web Text)

Max Activating Token Index: 552

Text #18

Max Range: 1.8549. Min Range: -1.8549

Max Act: 1.7526. Min Act: -0.1672

Data Index: 8363857 (Open Web Text)

Max Activating Token Index: 382

Text #19

Max Range: 1.8549. Min Range: -1.8549

Max Act: 1.7553. Min Act: -0.1579

Data Index: 7396490 (Open Web Text)

Max Activating Token Index: 739