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

Dataset: Open Web Text

Neuron 1526 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: 1.4763. Min Range: -1.4763

Max Act: 1.4763. Min Act: -0.1699

Data Index: 936211 (Open Web Text)

Max Activating Token Index: 359

Text #1

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.4413. Min Act: -0.1699

Data Index: 319695 (Open Web Text)

Max Activating Token Index: 288

Text #2

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.4343. Min Act: -0.1700

Data Index: 1975304 (Open Web Text)

Max Activating Token Index: 830

Text #3

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.4346. Min Act: -0.1700

Data Index: 6674107 (Open Web Text)

Max Activating Token Index: 360

Text #4

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.4125. Min Act: -0.1700

Data Index: 6061119 (Open Web Text)

Max Activating Token Index: 376

Text #5

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.4146. Min Act: -0.1691

Data Index: 3898038 (Open Web Text)

Max Activating Token Index: 344

Text #6

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.3947. Min Act: -0.1697

Data Index: 7659308 (Open Web Text)

Max Activating Token Index: 544

Text #7

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.3838. Min Act: -0.1699

Data Index: 6817480 (Open Web Text)

Max Activating Token Index: 577

Text #8

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.3811. Min Act: -0.1700

Data Index: 375269 (Open Web Text)

Max Activating Token Index: 333

Text #9

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.3860. Min Act: -0.1654

Data Index: 840435 (Open Web Text)

Max Activating Token Index: 690

Text #10

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.3718. Min Act: -0.1700

Data Index: 4817071 (Open Web Text)

Max Activating Token Index: 328

Text #11

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.3648. Min Act: -0.1700

Data Index: 6161774 (Open Web Text)

Max Activating Token Index: 296

Text #12

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.3630. Min Act: -0.1700

Data Index: 1531796 (Open Web Text)

Max Activating Token Index: 306

Text #13

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.3625. Min Act: -0.1700

Data Index: 1384872 (Open Web Text)

Max Activating Token Index: 281

Text #14

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.3680. Min Act: -0.1670

Data Index: 4603521 (Open Web Text)

Max Activating Token Index: 918

Text #15

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.3602. Min Act: -0.1700

Data Index: 8063446 (Open Web Text)

Max Activating Token Index: 539

Text #16

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.3655. Min Act: -0.1700

Data Index: 1975305 (Open Web Text)

Max Activating Token Index: 563

Text #17

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.3700. Min Act: -0.1698

Data Index: 26864 (Open Web Text)

Max Activating Token Index: 143

Text #18

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.3492. Min Act: -0.1700

Data Index: 375268 (Open Web Text)

Max Activating Token Index: 237

Text #19

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.3557. Min Act: -0.1700

Data Index: 5023932 (Open Web Text)

Max Activating Token Index: 312