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

Dataset: Open Web Text

Neuron 2731 in Layer 5

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: 4.5163. Min Range: -4.5163

Max Act: 4.5015. Min Act: -0.1700

Data Index: 660660 (Open Web Text)

Max Activating Token Index: 123

Text #1

Max Range: 4.5163. Min Range: -4.5163

Max Act: 4.4979. Min Act: -0.1700

Data Index: 639288 (Open Web Text)

Max Activating Token Index: 325

Text #2

Max Range: 4.5163. Min Range: -4.5163

Max Act: 4.5077. Min Act: -0.1700

Data Index: 7687519 (Open Web Text)

Max Activating Token Index: 409

Text #3

Max Range: 4.5163. Min Range: -4.5163

Max Act: 4.5163. Min Act: -0.1700

Data Index: 1692670 (Open Web Text)

Max Activating Token Index: 771

Text #4

Max Range: 4.5163. Min Range: -4.5163

Max Act: 4.5041. Min Act: -0.1700

Data Index: 8086325 (Open Web Text)

Max Activating Token Index: 995

Text #5

Max Range: 4.5163. Min Range: -4.5163

Max Act: 4.4606. Min Act: -0.1700

Data Index: 7436492 (Open Web Text)

Max Activating Token Index: 916

Text #6

Max Range: 4.5163. Min Range: -4.5163

Max Act: 4.4518. Min Act: -0.1700

Data Index: 3554111 (Open Web Text)

Max Activating Token Index: 764

Text #7

Max Range: 4.5163. Min Range: -4.5163

Max Act: 4.4912. Min Act: -0.1700

Data Index: 8481580 (Open Web Text)

Max Activating Token Index: 767

Text #8

Max Range: 4.5163. Min Range: -4.5163

Max Act: 4.4782. Min Act: -0.1700

Data Index: 5215772 (Open Web Text)

Max Activating Token Index: 560

Text #9

Max Range: 4.5163. Min Range: -4.5163

Max Act: 4.4688. Min Act: -0.1700

Data Index: 3319903 (Open Web Text)

Max Activating Token Index: 995

Text #10

Max Range: 4.5163. Min Range: -4.5163

Max Act: 4.4793. Min Act: -0.1700

Data Index: 96687 (Open Web Text)

Max Activating Token Index: 312

Text #11

Max Range: 4.5163. Min Range: -4.5163

Max Act: 4.4743. Min Act: -0.1700

Data Index: 4910442 (Open Web Text)

Max Activating Token Index: 938

Text #12

Max Range: 4.5163. Min Range: -4.5163

Max Act: 4.5066. Min Act: -0.1700

Data Index: 4375538 (Open Web Text)

Max Activating Token Index: 533

Text #13

Max Range: 4.5163. Min Range: -4.5163

Max Act: 4.4762. Min Act: -0.1700

Data Index: 4208865 (Open Web Text)

Max Activating Token Index: 328

Text #14

Max Range: 4.5163. Min Range: -4.5163

Max Act: 4.4635. Min Act: -0.1700

Data Index: 3981534 (Open Web Text)

Max Activating Token Index: 427

Text #15

Max Range: 4.5163. Min Range: -4.5163

Max Act: 4.4588. Min Act: -0.1700

Data Index: 2187119 (Open Web Text)

Max Activating Token Index: 811

Text #16

Max Range: 4.5163. Min Range: -4.5163

Max Act: 4.4543. Min Act: -0.1700

Data Index: 5660739 (Open Web Text)

Max Activating Token Index: 287

Text #17

Max Range: 4.5163. Min Range: -4.5163

Max Act: 4.4283. Min Act: -0.1700

Data Index: 2484459 (Open Web Text)

Max Activating Token Index: 868

Text #18

Max Range: 4.5163. Min Range: -4.5163

Max Act: 4.4376. Min Act: -0.1700

Data Index: 5728455 (Open Web Text)

Max Activating Token Index: 912

Text #19

Max Range: 4.5163. Min Range: -4.5163

Max Act: 4.4551. Min Act: -0.1700

Data Index: 3815420 (Open Web Text)

Max Activating Token Index: 1006