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

Dataset: Open Web Text

Neuron 2712 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: 3.5623. Min Range: -3.5623

Max Act: 3.5623. Min Act: -0.1700

Data Index: 2237311 (Open Web Text)

Max Activating Token Index: 664

Text #1

Max Range: 3.5623. Min Range: -3.5623

Max Act: 3.3311. Min Act: -0.1700

Data Index: 959702 (Open Web Text)

Max Activating Token Index: 305

Text #2

Max Range: 3.5623. Min Range: -3.5623

Max Act: 3.2216. Min Act: -0.1700

Data Index: 2862546 (Open Web Text)

Max Activating Token Index: 745

Text #3

Max Range: 3.5623. Min Range: -3.5623

Max Act: 3.1968. Min Act: -0.1700

Data Index: 7309686 (Open Web Text)

Max Activating Token Index: 971

Text #4

Max Range: 3.5623. Min Range: -3.5623

Max Act: 3.2035. Min Act: -0.1700

Data Index: 4588773 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 3.5623. Min Range: -3.5623

Max Act: 3.1706. Min Act: -0.1700

Data Index: 4569067 (Open Web Text)

Max Activating Token Index: 640

Text #6

Max Range: 3.5623. Min Range: -3.5623

Max Act: 3.2065. Min Act: -0.1700

Data Index: 350271 (Open Web Text)

Max Activating Token Index: 666

Text #7

Max Range: 3.5623. Min Range: -3.5623

Max Act: 3.1661. Min Act: -0.1700

Data Index: 5380347 (Open Web Text)

Max Activating Token Index: 1004

Text #8

Max Range: 3.5623. Min Range: -3.5623

Max Act: 3.1600. Min Act: -0.1700

Data Index: 4049704 (Open Web Text)

Max Activating Token Index: 508

Text #9

Max Range: 3.5623. Min Range: -3.5623

Max Act: 3.1263. Min Act: -0.1700

Data Index: 7428090 (Open Web Text)

Max Activating Token Index: 539

Text #10

Max Range: 3.5623. Min Range: -3.5623

Max Act: 3.1502. Min Act: -0.1700

Data Index: 8690748 (Open Web Text)

Max Activating Token Index: 319

Text #11

Max Range: 3.5623. Min Range: -3.5623

Max Act: 3.0898. Min Act: -0.1700

Data Index: 1910132 (Open Web Text)

Max Activating Token Index: 536

Text #12

Max Range: 3.5623. Min Range: -3.5623

Max Act: 3.1234. Min Act: -0.1700

Data Index: 3007928 (Open Web Text)

Max Activating Token Index: 530

Text #13

Max Range: 3.5623. Min Range: -3.5623

Max Act: 3.1350. Min Act: -0.1700

Data Index: 3797442 (Open Web Text)

Max Activating Token Index: 106

Text #14

Max Range: 3.5623. Min Range: -3.5623

Max Act: 3.1185. Min Act: -0.1700

Data Index: 1669896 (Open Web Text)

Max Activating Token Index: 321

Text #15

Max Range: 3.5623. Min Range: -3.5623

Max Act: 3.1256. Min Act: -0.1700

Data Index: 590117 (Open Web Text)

Max Activating Token Index: 500

Text #16

Max Range: 3.5623. Min Range: -3.5623

Max Act: 3.1331. Min Act: -0.1700

Data Index: 3082939 (Open Web Text)

Max Activating Token Index: 321

Text #17

Max Range: 3.5623. Min Range: -3.5623

Max Act: 3.0834. Min Act: -0.1700

Data Index: 4645912 (Open Web Text)

Max Activating Token Index: 491

Text #18

Max Range: 3.5623. Min Range: -3.5623

Max Act: 3.1283. Min Act: -0.1700

Data Index: 4519546 (Open Web Text)

Max Activating Token Index: 877

Text #19

Max Range: 3.5623. Min Range: -3.5623

Max Act: 3.0881. Min Act: -0.1700

Data Index: 3294329 (Open Web Text)

Max Activating Token Index: 781