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

Dataset: Open Web Text

Neuron 203 in Layer 3

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: 3.3266. Min Range: -3.3266

Max Act: 3.3266. Min Act: -0.1700

Data Index: 3674605 (Open Web Text)

Max Activating Token Index: 992

Text #1

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2905. Min Act: -0.1700

Data Index: 3003710 (Open Web Text)

Max Activating Token Index: 472

Text #2

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.3053. Min Act: -0.1700

Data Index: 5876614 (Open Web Text)

Max Activating Token Index: 441

Text #3

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2788. Min Act: -0.1700

Data Index: 2252853 (Open Web Text)

Max Activating Token Index: 85

Text #4

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2356. Min Act: -0.1700

Data Index: 6705325 (Open Web Text)

Max Activating Token Index: 654

Text #5

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2347. Min Act: -0.1700

Data Index: 2970148 (Open Web Text)

Max Activating Token Index: 381

Text #6

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1992. Min Act: -0.1700

Data Index: 2746731 (Open Web Text)

Max Activating Token Index: 799

Text #7

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2016. Min Act: -0.1700

Data Index: 2997876 (Open Web Text)

Max Activating Token Index: 973

Text #8

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1983. Min Act: -0.1700

Data Index: 3950255 (Open Web Text)

Max Activating Token Index: 105

Text #9

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1704. Min Act: -0.1700

Data Index: 7605565 (Open Web Text)

Max Activating Token Index: 179

Text #10

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1829. Min Act: -0.1700

Data Index: 2529371 (Open Web Text)

Max Activating Token Index: 774

Text #11

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1888. Min Act: -0.1700

Data Index: 5922968 (Open Web Text)

Max Activating Token Index: 307

Text #12

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1970. Min Act: -0.1700

Data Index: 7866159 (Open Web Text)

Max Activating Token Index: 778

Text #13

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1632. Min Act: -0.1700

Data Index: 4757792 (Open Web Text)

Max Activating Token Index: 803

Text #14

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1493. Min Act: -0.1700

Data Index: 6566838 (Open Web Text)

Max Activating Token Index: 364

Text #15

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1283. Min Act: -0.1700

Data Index: 949620 (Open Web Text)

Max Activating Token Index: 900

Text #16

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1365. Min Act: -0.1700

Data Index: 7324275 (Open Web Text)

Max Activating Token Index: 367

Text #17

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1371. Min Act: -0.1700

Data Index: 4829497 (Open Web Text)

Max Activating Token Index: 614

Text #18

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1375. Min Act: -0.1700

Data Index: 458417 (Open Web Text)

Max Activating Token Index: 570

Text #19

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1221. Min Act: -0.1700

Data Index: 7550291 (Open Web Text)

Max Activating Token Index: 356