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

Dataset: Open Web Text

Neuron 2761 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: 2.7821. Min Range: -2.7821

Max Act: 2.7821. Min Act: -0.1700

Data Index: 1834526 (Open Web Text)

Max Activating Token Index: 894

Text #1

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.7515. Min Act: -0.1700

Data Index: 8503832 (Open Web Text)

Max Activating Token Index: 232

Text #2

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.7310. Min Act: -0.1700

Data Index: 1306567 (Open Web Text)

Max Activating Token Index: 678

Text #3

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.6837. Min Act: -0.1700

Data Index: 3800487 (Open Web Text)

Max Activating Token Index: 931

Text #4

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.6905. Min Act: -0.1700

Data Index: 8601826 (Open Web Text)

Max Activating Token Index: 787

Text #5

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.7134. Min Act: -0.1700

Data Index: 4524202 (Open Web Text)

Max Activating Token Index: 886

Text #6

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.7092. Min Act: -0.1700

Data Index: 2018816 (Open Web Text)

Max Activating Token Index: 725

Text #7

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.6738. Min Act: -0.1700

Data Index: 7506376 (Open Web Text)

Max Activating Token Index: 621

Text #8

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.6745. Min Act: -0.1700

Data Index: 1905569 (Open Web Text)

Max Activating Token Index: 231

Text #9

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.6690. Min Act: -0.1700

Data Index: 1916127 (Open Web Text)

Max Activating Token Index: 61

Text #10

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.6724. Min Act: -0.1700

Data Index: 8241624 (Open Web Text)

Max Activating Token Index: 543

Text #11

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.6614. Min Act: -0.1700

Data Index: 5646027 (Open Web Text)

Max Activating Token Index: 1016

Text #12

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.6341. Min Act: -0.1700

Data Index: 1326545 (Open Web Text)

Max Activating Token Index: 972

Text #13

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.6232. Min Act: -0.1700

Data Index: 3012918 (Open Web Text)

Max Activating Token Index: 469

Text #14

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.6376. Min Act: -0.1700

Data Index: 5193402 (Open Web Text)

Max Activating Token Index: 91

Text #15

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.6279. Min Act: -0.1700

Data Index: 2974076 (Open Web Text)

Max Activating Token Index: 48

Text #16

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.6548. Min Act: -0.1700

Data Index: 2954931 (Open Web Text)

Max Activating Token Index: 38

Text #17

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.6411. Min Act: -0.1700

Data Index: 754845 (Open Web Text)

Max Activating Token Index: 350

Text #18

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.6416. Min Act: -0.1700

Data Index: 1136222 (Open Web Text)

Max Activating Token Index: 221

Text #19

Max Range: 2.7821. Min Range: -2.7821

Max Act: 2.6294. Min Act: -0.1700

Data Index: 6166054 (Open Web Text)

Max Activating Token Index: 398