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

Dataset: Open Web Text

Neuron 1727 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: 2.5765. Min Range: -2.5765

Max Act: 2.5765. Min Act: -0.1687

Data Index: 6630812 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.5765. Min Range: -2.5765

Max Act: 2.5571. Min Act: -0.1700

Data Index: 8658683 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.5765. Min Range: -2.5765

Max Act: 2.5702. Min Act: -0.1491

Data Index: 2443566 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.5765. Min Range: -2.5765

Max Act: 2.5593. Min Act: -0.1697

Data Index: 1734322 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.5765. Min Range: -2.5765

Max Act: 2.5429. Min Act: -0.1699

Data Index: 3817518 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.5765. Min Range: -2.5765

Max Act: 2.5170. Min Act: -0.1617

Data Index: 1808095 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.5765. Min Range: -2.5765

Max Act: 2.5365. Min Act: -0.1615

Data Index: 1898755 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 2.5765. Min Range: -2.5765

Max Act: 2.4895. Min Act: -0.1700

Data Index: 2203290 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.5765. Min Range: -2.5765

Max Act: 2.4931. Min Act: -0.1700

Data Index: 2817565 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 2.5765. Min Range: -2.5765

Max Act: 2.4919. Min Act: -0.1443

Data Index: 5382604 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 2.5765. Min Range: -2.5765

Max Act: 2.4840. Min Act: -0.1699

Data Index: 4162368 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 2.5765. Min Range: -2.5765

Max Act: 2.4484. Min Act: -0.1579

Data Index: 5736865 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 2.5765. Min Range: -2.5765

Max Act: 2.4568. Min Act: -0.1626

Data Index: 1652927 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.5765. Min Range: -2.5765

Max Act: 2.4175. Min Act: -0.1486

Data Index: 8686271 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 2.5765. Min Range: -2.5765

Max Act: 2.4439. Min Act: -0.1620

Data Index: 6885080 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.5765. Min Range: -2.5765

Max Act: 2.4317. Min Act: -0.1691

Data Index: 3490483 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 2.5765. Min Range: -2.5765

Max Act: 2.4225. Min Act: -0.1687

Data Index: 7246259 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 2.5765. Min Range: -2.5765

Max Act: 2.4213. Min Act: -0.1700

Data Index: 8452784 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.5765. Min Range: -2.5765

Max Act: 2.4120. Min Act: -0.1689

Data Index: 6729419 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.5765. Min Range: -2.5765

Max Act: 2.4344. Min Act: -0.1350

Data Index: 4810533 (Open Web Text)

Max Activating Token Index: 1023