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

Dataset: Open Web Text

Neuron 429 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: 3.4158. Min Range: -3.4158

Max Act: 3.4158. Min Act: -0.1700

Data Index: 3854442 (Open Web Text)

Max Activating Token Index: 638

Text #1

Max Range: 3.4158. Min Range: -3.4158

Max Act: 3.3449. Min Act: -0.1700

Data Index: 2011225 (Open Web Text)

Max Activating Token Index: 558

Text #2

Max Range: 3.4158. Min Range: -3.4158

Max Act: 3.3013. Min Act: -0.1700

Data Index: 3439833 (Open Web Text)

Max Activating Token Index: 511

Text #3

Max Range: 3.4158. Min Range: -3.4158

Max Act: 3.2922. Min Act: -0.1700

Data Index: 388657 (Open Web Text)

Max Activating Token Index: 531

Text #4

Max Range: 3.4158. Min Range: -3.4158

Max Act: 3.2899. Min Act: -0.1700

Data Index: 5507877 (Open Web Text)

Max Activating Token Index: 729

Text #5

Max Range: 3.4158. Min Range: -3.4158

Max Act: 3.2418. Min Act: -0.1700

Data Index: 7731229 (Open Web Text)

Max Activating Token Index: 895

Text #6

Max Range: 3.4158. Min Range: -3.4158

Max Act: 3.2332. Min Act: -0.1700

Data Index: 6203824 (Open Web Text)

Max Activating Token Index: 189

Text #7

Max Range: 3.4158. Min Range: -3.4158

Max Act: 3.2321. Min Act: -0.1700

Data Index: 3201711 (Open Web Text)

Max Activating Token Index: 494

Text #8

Max Range: 3.4158. Min Range: -3.4158

Max Act: 3.2293. Min Act: -0.1700

Data Index: 1962260 (Open Web Text)

Max Activating Token Index: 910

Text #9

Max Range: 3.4158. Min Range: -3.4158

Max Act: 3.1889. Min Act: -0.1700

Data Index: 4583045 (Open Web Text)

Max Activating Token Index: 22

Text #10

Max Range: 3.4158. Min Range: -3.4158

Max Act: 3.1760. Min Act: -0.1700

Data Index: 1043113 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.4158. Min Range: -3.4158

Max Act: 3.1532. Min Act: -0.1700

Data Index: 8235011 (Open Web Text)

Max Activating Token Index: 150

Text #12

Max Range: 3.4158. Min Range: -3.4158

Max Act: 3.1604. Min Act: -0.1700

Data Index: 8460873 (Open Web Text)

Max Activating Token Index: 666

Text #13

Max Range: 3.4158. Min Range: -3.4158

Max Act: 3.1585. Min Act: -0.1700

Data Index: 2930781 (Open Web Text)

Max Activating Token Index: 393

Text #14

Max Range: 3.4158. Min Range: -3.4158

Max Act: 3.1434. Min Act: -0.1700

Data Index: 8496136 (Open Web Text)

Max Activating Token Index: 788

Text #15

Max Range: 3.4158. Min Range: -3.4158

Max Act: 3.1384. Min Act: -0.1700

Data Index: 6450809 (Open Web Text)

Max Activating Token Index: 376

Text #16

Max Range: 3.4158. Min Range: -3.4158

Max Act: 3.1402. Min Act: -0.1700

Data Index: 5997372 (Open Web Text)

Max Activating Token Index: 290

Text #17

Max Range: 3.4158. Min Range: -3.4158

Max Act: 3.1568. Min Act: -0.1700

Data Index: 4184897 (Open Web Text)

Max Activating Token Index: 450

Text #18

Max Range: 3.4158. Min Range: -3.4158

Max Act: 3.1269. Min Act: -0.1700

Data Index: 7823599 (Open Web Text)

Max Activating Token Index: 587

Text #19

Max Range: 3.4158. Min Range: -3.4158

Max Act: 3.1405. Min Act: -0.1700

Data Index: 4173114 (Open Web Text)

Max Activating Token Index: 521