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

Dataset: Open Web Text

Neuron 1261 in Layer 0

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: 5.4474. Min Range: -5.4474

Max Act: 5.4474. Min Act: -0.1700

Data Index: 196553 (Open Web Text)

Max Activating Token Index: 988

Text #1

Max Range: 5.4474. Min Range: -5.4474

Max Act: 5.2829. Min Act: -0.1700

Data Index: 1334824 (Open Web Text)

Max Activating Token Index: 900

Text #2

Max Range: 5.4474. Min Range: -5.4474

Max Act: 5.2346. Min Act: -0.1700

Data Index: 8676140 (Open Web Text)

Max Activating Token Index: 1015

Text #3

Max Range: 5.4474. Min Range: -5.4474

Max Act: 5.2827. Min Act: -0.1700

Data Index: 7102279 (Open Web Text)

Max Activating Token Index: 702

Text #4

Max Range: 5.4474. Min Range: -5.4474

Max Act: 5.2686. Min Act: -0.1700

Data Index: 4373788 (Open Web Text)

Max Activating Token Index: 555

Text #5

Max Range: 5.4474. Min Range: -5.4474

Max Act: 5.2523. Min Act: -0.1700

Data Index: 3303715 (Open Web Text)

Max Activating Token Index: 834

Text #6

Max Range: 5.4474. Min Range: -5.4474

Max Act: 5.2037. Min Act: -0.1700

Data Index: 7246126 (Open Web Text)

Max Activating Token Index: 879

Text #7

Max Range: 5.4474. Min Range: -5.4474

Max Act: 5.2256. Min Act: -0.1700

Data Index: 3682739 (Open Web Text)

Max Activating Token Index: 408

Text #8

Max Range: 5.4474. Min Range: -5.4474

Max Act: 5.2052. Min Act: -0.1700

Data Index: 1671687 (Open Web Text)

Max Activating Token Index: 769

Text #9

Max Range: 5.4474. Min Range: -5.4474

Max Act: 5.1968. Min Act: -0.1700

Data Index: 4498089 (Open Web Text)

Max Activating Token Index: 701

Text #10

Max Range: 5.4474. Min Range: -5.4474

Max Act: 5.2092. Min Act: -0.1700

Data Index: 1789072 (Open Web Text)

Max Activating Token Index: 701

Text #11

Max Range: 5.4474. Min Range: -5.4474

Max Act: 5.1481. Min Act: -0.1700

Data Index: 6808409 (Open Web Text)

Max Activating Token Index: 907

Text #12

Max Range: 5.4474. Min Range: -5.4474

Max Act: 5.1739. Min Act: -0.1700

Data Index: 5908397 (Open Web Text)

Max Activating Token Index: 1016

Text #13

Max Range: 5.4474. Min Range: -5.4474

Max Act: 5.1784. Min Act: -0.1700

Data Index: 2136470 (Open Web Text)

Max Activating Token Index: 960

Text #14

Max Range: 5.4474. Min Range: -5.4474

Max Act: 5.0900. Min Act: -0.1700

Data Index: 7322895 (Open Web Text)

Max Activating Token Index: 890

Text #15

Max Range: 5.4474. Min Range: -5.4474

Max Act: 5.1267. Min Act: -0.1700

Data Index: 7035401 (Open Web Text)

Max Activating Token Index: 861

Text #16

Max Range: 5.4474. Min Range: -5.4474

Max Act: 5.1046. Min Act: -0.1700

Data Index: 4307509 (Open Web Text)

Max Activating Token Index: 882

Text #17

Max Range: 5.4474. Min Range: -5.4474

Max Act: 5.1516. Min Act: -0.1700

Data Index: 4875848 (Open Web Text)

Max Activating Token Index: 23

Text #18

Max Range: 5.4474. Min Range: -5.4474

Max Act: 5.0963. Min Act: -0.1700

Data Index: 2358536 (Open Web Text)

Max Activating Token Index: 781

Text #19

Max Range: 5.4474. Min Range: -5.4474

Max Act: 5.1274. Min Act: -0.1700

Data Index: 6759717 (Open Web Text)

Max Activating Token Index: 999