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

Dataset: Open Web Text

Neuron 1433 in Layer 2

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: 2.6339. Min Range: -2.6339

Max Act: 2.6339. Min Act: -0.1700

Data Index: 4458259 (Open Web Text)

Max Activating Token Index: 308

Text #1

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.6083. Min Act: -0.1700

Data Index: 6819337 (Open Web Text)

Max Activating Token Index: 688

Text #2

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.5898. Min Act: -0.1700

Data Index: 1491234 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.5395. Min Act: -0.1700

Data Index: 3753026 (Open Web Text)

Max Activating Token Index: 468

Text #4

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.5129. Min Act: -0.1700

Data Index: 3273463 (Open Web Text)

Max Activating Token Index: 58

Text #5

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.4603. Min Act: -0.1700

Data Index: 536747 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.4894. Min Act: -0.1700

Data Index: 6388625 (Open Web Text)

Max Activating Token Index: 139

Text #7

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.4662. Min Act: -0.1700

Data Index: 5439280 (Open Web Text)

Max Activating Token Index: 376

Text #8

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.4234. Min Act: -0.1700

Data Index: 2738718 (Open Web Text)

Max Activating Token Index: 311

Text #9

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.4291. Min Act: -0.1700

Data Index: 5240075 (Open Web Text)

Max Activating Token Index: 553

Text #10

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.4216. Min Act: -0.1700

Data Index: 8105504 (Open Web Text)

Max Activating Token Index: 21

Text #11

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.4194. Min Act: -0.1700

Data Index: 2607483 (Open Web Text)

Max Activating Token Index: 326

Text #12

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.4204. Min Act: -0.1700

Data Index: 2286596 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.4219. Min Act: -0.1700

Data Index: 8742823 (Open Web Text)

Max Activating Token Index: 45

Text #14

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.3887. Min Act: -0.1700

Data Index: 2171875 (Open Web Text)

Max Activating Token Index: 38

Text #15

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.3876. Min Act: -0.1700

Data Index: 6488516 (Open Web Text)

Max Activating Token Index: 500

Text #16

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.3674. Min Act: -0.1700

Data Index: 3839251 (Open Web Text)

Max Activating Token Index: 26

Text #17

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.3464. Min Act: -0.1700

Data Index: 2834276 (Open Web Text)

Max Activating Token Index: 503

Text #18

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.3475. Min Act: -0.1700

Data Index: 4092639 (Open Web Text)

Max Activating Token Index: 1020

Text #19

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.3509. Min Act: -0.1700

Data Index: 4719734 (Open Web Text)

Max Activating Token Index: 22