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

Dataset: Open Web Text

Neuron 903 in Layer 6

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: 3.9021. Min Range: -3.9021

Max Act: 3.9021. Min Act: -0.1700

Data Index: 1122984 (Open Web Text)

Max Activating Token Index: 597

Text #1

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.8805. Min Act: -0.1700

Data Index: 2491811 (Open Web Text)

Max Activating Token Index: 833

Text #2

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.8540. Min Act: -0.1700

Data Index: 1405109 (Open Web Text)

Max Activating Token Index: 702

Text #3

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.8651. Min Act: -0.1700

Data Index: 3865210 (Open Web Text)

Max Activating Token Index: 300

Text #4

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.8524. Min Act: -0.1700

Data Index: 4685663 (Open Web Text)

Max Activating Token Index: 420

Text #5

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.8389. Min Act: -0.1700

Data Index: 1894394 (Open Web Text)

Max Activating Token Index: 318

Text #6

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.8117. Min Act: -0.1700

Data Index: 6088943 (Open Web Text)

Max Activating Token Index: 774

Text #7

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.8309. Min Act: -0.1700

Data Index: 6548855 (Open Web Text)

Max Activating Token Index: 266

Text #8

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.8174. Min Act: -0.1700

Data Index: 5064372 (Open Web Text)

Max Activating Token Index: 511

Text #9

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.8046. Min Act: -0.1700

Data Index: 2029401 (Open Web Text)

Max Activating Token Index: 349

Text #10

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.7703. Min Act: -0.1700

Data Index: 2511636 (Open Web Text)

Max Activating Token Index: 569

Text #11

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.7760. Min Act: -0.1700

Data Index: 8399121 (Open Web Text)

Max Activating Token Index: 76

Text #12

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.7811. Min Act: -0.1700

Data Index: 5026896 (Open Web Text)

Max Activating Token Index: 328

Text #13

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.7818. Min Act: -0.1700

Data Index: 4904946 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.7629. Min Act: -0.1700

Data Index: 3339034 (Open Web Text)

Max Activating Token Index: 456

Text #15

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.7483. Min Act: -0.1700

Data Index: 5064373 (Open Web Text)

Max Activating Token Index: 286

Text #16

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.7494. Min Act: -0.1700

Data Index: 5146459 (Open Web Text)

Max Activating Token Index: 993

Text #17

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.7379. Min Act: -0.1700

Data Index: 16488 (Open Web Text)

Max Activating Token Index: 455

Text #18

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.7215. Min Act: -0.1700

Data Index: 6044167 (Open Web Text)

Max Activating Token Index: 582

Text #19

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.7189. Min Act: -0.1700

Data Index: 3859385 (Open Web Text)

Max Activating Token Index: 856