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

Dataset: Open Web Text

Neuron 799 in Layer 4

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: 3.6184. Min Range: -3.6184

Max Act: 3.6184. Min Act: -0.1700

Data Index: 4034813 (Open Web Text)

Max Activating Token Index: 643

Text #1

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.5748. Min Act: -0.1700

Data Index: 3720846 (Open Web Text)

Max Activating Token Index: 52

Text #2

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.5748. Min Act: -0.1700

Data Index: 1890107 (Open Web Text)

Max Activating Token Index: 682

Text #3

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.5266. Min Act: -0.1700

Data Index: 565979 (Open Web Text)

Max Activating Token Index: 481

Text #4

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.5057. Min Act: -0.1700

Data Index: 4996665 (Open Web Text)

Max Activating Token Index: 456

Text #5

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.4751. Min Act: -0.1700

Data Index: 6002097 (Open Web Text)

Max Activating Token Index: 430

Text #6

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.4744. Min Act: -0.1700

Data Index: 7590826 (Open Web Text)

Max Activating Token Index: 455

Text #7

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.4649. Min Act: -0.1700

Data Index: 1087627 (Open Web Text)

Max Activating Token Index: 560

Text #8

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.4581. Min Act: -0.1700

Data Index: 4961103 (Open Web Text)

Max Activating Token Index: 568

Text #9

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.4413. Min Act: -0.1700

Data Index: 5270417 (Open Web Text)

Max Activating Token Index: 20

Text #10

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.4561. Min Act: -0.1700

Data Index: 6815926 (Open Web Text)

Max Activating Token Index: 641

Text #11

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.4335. Min Act: -0.1700

Data Index: 6552597 (Open Web Text)

Max Activating Token Index: 703

Text #12

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.4431. Min Act: -0.1700

Data Index: 7005504 (Open Web Text)

Max Activating Token Index: 458

Text #13

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.4117. Min Act: -0.1700

Data Index: 7104427 (Open Web Text)

Max Activating Token Index: 558

Text #14

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.4426. Min Act: -0.1700

Data Index: 2128087 (Open Web Text)

Max Activating Token Index: 624

Text #15

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.4131. Min Act: -0.1700

Data Index: 2199300 (Open Web Text)

Max Activating Token Index: 413

Text #16

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.4122. Min Act: -0.1700

Data Index: 6129306 (Open Web Text)

Max Activating Token Index: 582

Text #17

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.4244. Min Act: -0.1700

Data Index: 8821618 (Open Web Text)

Max Activating Token Index: 680

Text #18

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.4457. Min Act: -0.1700

Data Index: 1244583 (Open Web Text)

Max Activating Token Index: 424

Text #19

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.4348. Min Act: -0.1700

Data Index: 2047440 (Open Web Text)

Max Activating Token Index: 154