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

Dataset: Open Web Text

Neuron 2000 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: 1.7547. Min Range: -1.7547

Max Act: 1.7547. Min Act: -0.1693

Data Index: 5039238 (Open Web Text)

Max Activating Token Index: 138

Text #1

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6832. Min Act: -0.1700

Data Index: 4620796 (Open Web Text)

Max Activating Token Index: 516

Text #2

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6833. Min Act: -0.1695

Data Index: 314111 (Open Web Text)

Max Activating Token Index: 704

Text #3

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6780. Min Act: -0.1697

Data Index: 3130040 (Open Web Text)

Max Activating Token Index: 308

Text #4

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6707. Min Act: -0.1694

Data Index: 4957103 (Open Web Text)

Max Activating Token Index: 325

Text #5

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6645. Min Act: -0.1696

Data Index: 5322686 (Open Web Text)

Max Activating Token Index: 285

Text #6

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6539. Min Act: -0.1700

Data Index: 2802850 (Open Web Text)

Max Activating Token Index: 516

Text #7

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6521. Min Act: -0.1687

Data Index: 4131014 (Open Web Text)

Max Activating Token Index: 330

Text #8

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6539. Min Act: -0.1700

Data Index: 5362362 (Open Web Text)

Max Activating Token Index: 748

Text #9

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6508. Min Act: -0.1700

Data Index: 8709714 (Open Web Text)

Max Activating Token Index: 312

Text #10

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6491. Min Act: -0.1696

Data Index: 2634042 (Open Web Text)

Max Activating Token Index: 524

Text #11

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6495. Min Act: -0.1700

Data Index: 2802851 (Open Web Text)

Max Activating Token Index: 954

Text #12

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6490. Min Act: -0.1700

Data Index: 5545462 (Open Web Text)

Max Activating Token Index: 507

Text #13

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6436. Min Act: -0.1699

Data Index: 8606644 (Open Web Text)

Max Activating Token Index: 336

Text #14

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6454. Min Act: -0.1700

Data Index: 271381 (Open Web Text)

Max Activating Token Index: 818

Text #15

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6521. Min Act: -0.1698

Data Index: 7072557 (Open Web Text)

Max Activating Token Index: 785

Text #16

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6403. Min Act: -0.1700

Data Index: 8672133 (Open Web Text)

Max Activating Token Index: 895

Text #17

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6298. Min Act: -0.1700

Data Index: 4485769 (Open Web Text)

Max Activating Token Index: 190

Text #18

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6311. Min Act: -0.1700

Data Index: 59458 (Open Web Text)

Max Activating Token Index: 680

Text #19

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6307. Min Act: -0.1700

Data Index: 5332087 (Open Web Text)

Max Activating Token Index: 711