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

Dataset: Open Web Text

Neuron 2458 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: 3.8640. Min Range: -3.8640

Max Act: 3.8461. Min Act: -0.1700

Data Index: 105740 (Open Web Text)

Max Activating Token Index: 741

Text #1

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.8640. Min Act: -0.1700

Data Index: 1581249 (Open Web Text)

Max Activating Token Index: 86

Text #2

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.8319. Min Act: -0.1700

Data Index: 720543 (Open Web Text)

Max Activating Token Index: 714

Text #3

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.7764. Min Act: -0.1700

Data Index: 5123558 (Open Web Text)

Max Activating Token Index: 864

Text #4

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.7941. Min Act: -0.1700

Data Index: 5159843 (Open Web Text)

Max Activating Token Index: 413

Text #5

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.7562. Min Act: -0.1700

Data Index: 3790710 (Open Web Text)

Max Activating Token Index: 194

Text #6

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.7505. Min Act: -0.1700

Data Index: 6544631 (Open Web Text)

Max Activating Token Index: 440

Text #7

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.7784. Min Act: -0.1700

Data Index: 8503188 (Open Web Text)

Max Activating Token Index: 858

Text #8

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.7651. Min Act: -0.1700

Data Index: 4090723 (Open Web Text)

Max Activating Token Index: 712

Text #9

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.7555. Min Act: -0.1700

Data Index: 2589046 (Open Web Text)

Max Activating Token Index: 419

Text #10

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.8021. Min Act: -0.1700

Data Index: 2771744 (Open Web Text)

Max Activating Token Index: 309

Text #11

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.7156. Min Act: -0.1700

Data Index: 4847590 (Open Web Text)

Max Activating Token Index: 328

Text #12

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.7309. Min Act: -0.1700

Data Index: 4454544 (Open Web Text)

Max Activating Token Index: 368

Text #13

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.7496. Min Act: -0.1700

Data Index: 391964 (Open Web Text)

Max Activating Token Index: 714

Text #14

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.7266. Min Act: -0.1700

Data Index: 1492463 (Open Web Text)

Max Activating Token Index: 920

Text #15

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.6797. Min Act: -0.1700

Data Index: 3445595 (Open Web Text)

Max Activating Token Index: 986

Text #16

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.6762. Min Act: -0.1700

Data Index: 2795086 (Open Web Text)

Max Activating Token Index: 333

Text #17

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.7103. Min Act: -0.1700

Data Index: 271401 (Open Web Text)

Max Activating Token Index: 434

Text #18

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.6918. Min Act: -0.1700

Data Index: 3528618 (Open Web Text)

Max Activating Token Index: 304

Text #19

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.6947. Min Act: -0.1700

Data Index: 2815774 (Open Web Text)

Max Activating Token Index: 460