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

Dataset: Open Web Text

Neuron 2717 in Layer 5

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: 4.6043. Min Range: -4.6043

Max Act: 4.6043. Min Act: -0.1700

Data Index: 3044403 (Open Web Text)

Max Activating Token Index: 431

Text #1

Max Range: 4.6043. Min Range: -4.6043

Max Act: 4.5573. Min Act: -0.1700

Data Index: 1958464 (Open Web Text)

Max Activating Token Index: 634

Text #2

Max Range: 4.6043. Min Range: -4.6043

Max Act: 4.4677. Min Act: -0.1700

Data Index: 6445887 (Open Web Text)

Max Activating Token Index: 446

Text #3

Max Range: 4.6043. Min Range: -4.6043

Max Act: 4.4177. Min Act: -0.1700

Data Index: 4747324 (Open Web Text)

Max Activating Token Index: 696

Text #4

Max Range: 4.6043. Min Range: -4.6043

Max Act: 4.3925. Min Act: -0.1700

Data Index: 7619593 (Open Web Text)

Max Activating Token Index: 273

Text #5

Max Range: 4.6043. Min Range: -4.6043

Max Act: 4.3625. Min Act: -0.1700

Data Index: 3688685 (Open Web Text)

Max Activating Token Index: 624

Text #6

Max Range: 4.6043. Min Range: -4.6043

Max Act: 4.3872. Min Act: -0.1700

Data Index: 3062050 (Open Web Text)

Max Activating Token Index: 394

Text #7

Max Range: 4.6043. Min Range: -4.6043

Max Act: 4.3340. Min Act: -0.1700

Data Index: 2541348 (Open Web Text)

Max Activating Token Index: 536

Text #8

Max Range: 4.6043. Min Range: -4.6043

Max Act: 4.2987. Min Act: -0.1700

Data Index: 473226 (Open Web Text)

Max Activating Token Index: 665

Text #9

Max Range: 4.6043. Min Range: -4.6043

Max Act: 4.2897. Min Act: -0.1700

Data Index: 2284895 (Open Web Text)

Max Activating Token Index: 472

Text #10

Max Range: 4.6043. Min Range: -4.6043

Max Act: 4.3394. Min Act: -0.1700

Data Index: 6274338 (Open Web Text)

Max Activating Token Index: 36

Text #11

Max Range: 4.6043. Min Range: -4.6043

Max Act: 4.3427. Min Act: -0.1700

Data Index: 6049621 (Open Web Text)

Max Activating Token Index: 332

Text #12

Max Range: 4.6043. Min Range: -4.6043

Max Act: 4.2830. Min Act: -0.1700

Data Index: 7883894 (Open Web Text)

Max Activating Token Index: 72

Text #13

Max Range: 4.6043. Min Range: -4.6043

Max Act: 4.2864. Min Act: -0.1700

Data Index: 4635386 (Open Web Text)

Max Activating Token Index: 336

Text #14

Max Range: 4.6043. Min Range: -4.6043

Max Act: 4.2730. Min Act: -0.1700

Data Index: 1660696 (Open Web Text)

Max Activating Token Index: 86

Text #15

Max Range: 4.6043. Min Range: -4.6043

Max Act: 4.2781. Min Act: -0.1700

Data Index: 2725500 (Open Web Text)

Max Activating Token Index: 104

Text #16

Max Range: 4.6043. Min Range: -4.6043

Max Act: 4.2653. Min Act: -0.1700

Data Index: 4759977 (Open Web Text)

Max Activating Token Index: 470

Text #17

Max Range: 4.6043. Min Range: -4.6043

Max Act: 4.2552. Min Act: -0.1700

Data Index: 2158361 (Open Web Text)

Max Activating Token Index: 658

Text #18

Max Range: 4.6043. Min Range: -4.6043

Max Act: 4.2875. Min Act: -0.1700

Data Index: 1536549 (Open Web Text)

Max Activating Token Index: 369

Text #19

Max Range: 4.6043. Min Range: -4.6043

Max Act: 4.2585. Min Act: -0.1700

Data Index: 3947515 (Open Web Text)

Max Activating Token Index: 701