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

Dataset: Open Web Text

Neuron 1618 in Layer 2

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: 3.5364. Min Range: -3.5364

Max Act: 3.5364. Min Act: -0.1700

Data Index: 4736860 (Open Web Text)

Max Activating Token Index: 993

Text #1

Max Range: 3.5364. Min Range: -3.5364

Max Act: 3.5146. Min Act: -0.1700

Data Index: 7499743 (Open Web Text)

Max Activating Token Index: 770

Text #2

Max Range: 3.5364. Min Range: -3.5364

Max Act: 3.4967. Min Act: -0.1700

Data Index: 2836752 (Open Web Text)

Max Activating Token Index: 933

Text #3

Max Range: 3.5364. Min Range: -3.5364

Max Act: 3.4660. Min Act: -0.1700

Data Index: 1136955 (Open Web Text)

Max Activating Token Index: 121

Text #4

Max Range: 3.5364. Min Range: -3.5364

Max Act: 3.4470. Min Act: -0.1700

Data Index: 5337826 (Open Web Text)

Max Activating Token Index: 589

Text #5

Max Range: 3.5364. Min Range: -3.5364

Max Act: 3.4396. Min Act: -0.1700

Data Index: 3866468 (Open Web Text)

Max Activating Token Index: 318

Text #6

Max Range: 3.5364. Min Range: -3.5364

Max Act: 3.4393. Min Act: -0.1700

Data Index: 5942292 (Open Web Text)

Max Activating Token Index: 121

Text #7

Max Range: 3.5364. Min Range: -3.5364

Max Act: 3.4263. Min Act: -0.1700

Data Index: 5919729 (Open Web Text)

Max Activating Token Index: 177

Text #8

Max Range: 3.5364. Min Range: -3.5364

Max Act: 3.4369. Min Act: -0.1700

Data Index: 2258533 (Open Web Text)

Max Activating Token Index: 444

Text #9

Max Range: 3.5364. Min Range: -3.5364

Max Act: 3.4039. Min Act: -0.1700

Data Index: 7825601 (Open Web Text)

Max Activating Token Index: 653

Text #10

Max Range: 3.5364. Min Range: -3.5364

Max Act: 3.4188. Min Act: -0.1700

Data Index: 1270898 (Open Web Text)

Max Activating Token Index: 315

Text #11

Max Range: 3.5364. Min Range: -3.5364

Max Act: 3.4067. Min Act: -0.1700

Data Index: 865877 (Open Web Text)

Max Activating Token Index: 107

Text #12

Max Range: 3.5364. Min Range: -3.5364

Max Act: 3.3946. Min Act: -0.1700

Data Index: 5087603 (Open Web Text)

Max Activating Token Index: 736

Text #13

Max Range: 3.5364. Min Range: -3.5364

Max Act: 3.3871. Min Act: -0.1700

Data Index: 8168846 (Open Web Text)

Max Activating Token Index: 196

Text #14

Max Range: 3.5364. Min Range: -3.5364

Max Act: 3.3839. Min Act: -0.1700

Data Index: 8730128 (Open Web Text)

Max Activating Token Index: 909

Text #15

Max Range: 3.5364. Min Range: -3.5364

Max Act: 3.3851. Min Act: -0.1700

Data Index: 6584343 (Open Web Text)

Max Activating Token Index: 522

Text #16

Max Range: 3.5364. Min Range: -3.5364

Max Act: 3.3772. Min Act: -0.1700

Data Index: 5058957 (Open Web Text)

Max Activating Token Index: 636

Text #17

Max Range: 3.5364. Min Range: -3.5364

Max Act: 3.3849. Min Act: -0.1700

Data Index: 2327314 (Open Web Text)

Max Activating Token Index: 757

Text #18

Max Range: 3.5364. Min Range: -3.5364

Max Act: 3.3887. Min Act: -0.1700

Data Index: 323750 (Open Web Text)

Max Activating Token Index: 595

Text #19

Max Range: 3.5364. Min Range: -3.5364

Max Act: 3.3715. Min Act: -0.1700

Data Index: 8013753 (Open Web Text)

Max Activating Token Index: 391