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

Dataset: Open Web Text

Neuron 719 in Layer 6

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: 3.4611. Min Range: -3.4611

Max Act: 3.4611. Min Act: -0.1700

Data Index: 5615617 (Open Web Text)

Max Activating Token Index: 874

Text #1

Max Range: 3.4611. Min Range: -3.4611

Max Act: 3.3890. Min Act: -0.1700

Data Index: 4843557 (Open Web Text)

Max Activating Token Index: 497

Text #2

Max Range: 3.4611. Min Range: -3.4611

Max Act: 3.3850. Min Act: -0.1700

Data Index: 7806745 (Open Web Text)

Max Activating Token Index: 279

Text #3

Max Range: 3.4611. Min Range: -3.4611

Max Act: 3.2897. Min Act: -0.1700

Data Index: 835333 (Open Web Text)

Max Activating Token Index: 395

Text #4

Max Range: 3.4611. Min Range: -3.4611

Max Act: 3.3070. Min Act: -0.1700

Data Index: 1557759 (Open Web Text)

Max Activating Token Index: 976

Text #5

Max Range: 3.4611. Min Range: -3.4611

Max Act: 3.2980. Min Act: -0.1700

Data Index: 2900697 (Open Web Text)

Max Activating Token Index: 771

Text #6

Max Range: 3.4611. Min Range: -3.4611

Max Act: 3.2725. Min Act: -0.1700

Data Index: 4652226 (Open Web Text)

Max Activating Token Index: 314

Text #7

Max Range: 3.4611. Min Range: -3.4611

Max Act: 3.2253. Min Act: -0.1700

Data Index: 6844845 (Open Web Text)

Max Activating Token Index: 515

Text #8

Max Range: 3.4611. Min Range: -3.4611

Max Act: 3.2550. Min Act: -0.1700

Data Index: 6281757 (Open Web Text)

Max Activating Token Index: 631

Text #9

Max Range: 3.4611. Min Range: -3.4611

Max Act: 3.2299. Min Act: -0.1700

Data Index: 8790392 (Open Web Text)

Max Activating Token Index: 246

Text #10

Max Range: 3.4611. Min Range: -3.4611

Max Act: 3.2217. Min Act: -0.1700

Data Index: 6649232 (Open Web Text)

Max Activating Token Index: 436

Text #11

Max Range: 3.4611. Min Range: -3.4611

Max Act: 3.2136. Min Act: -0.1700

Data Index: 5082568 (Open Web Text)

Max Activating Token Index: 732

Text #12

Max Range: 3.4611. Min Range: -3.4611

Max Act: 3.1975. Min Act: -0.1700

Data Index: 4430402 (Open Web Text)

Max Activating Token Index: 544

Text #13

Max Range: 3.4611. Min Range: -3.4611

Max Act: 3.2151. Min Act: -0.1700

Data Index: 5791947 (Open Web Text)

Max Activating Token Index: 774

Text #14

Max Range: 3.4611. Min Range: -3.4611

Max Act: 3.1586. Min Act: -0.1700

Data Index: 5006689 (Open Web Text)

Max Activating Token Index: 745

Text #15

Max Range: 3.4611. Min Range: -3.4611

Max Act: 3.1751. Min Act: -0.1700

Data Index: 1354138 (Open Web Text)

Max Activating Token Index: 580

Text #16

Max Range: 3.4611. Min Range: -3.4611

Max Act: 3.1643. Min Act: -0.1700

Data Index: 6068245 (Open Web Text)

Max Activating Token Index: 911

Text #17

Max Range: 3.4611. Min Range: -3.4611

Max Act: 3.1511. Min Act: -0.1700

Data Index: 8621060 (Open Web Text)

Max Activating Token Index: 867

Text #18

Max Range: 3.4611. Min Range: -3.4611

Max Act: 3.1652. Min Act: -0.1700

Data Index: 83469 (Open Web Text)

Max Activating Token Index: 885

Text #19

Max Range: 3.4611. Min Range: -3.4611

Max Act: 3.1490. Min Act: -0.1700

Data Index: 4273311 (Open Web Text)

Max Activating Token Index: 893