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

Dataset: Open Web Text

Neuron 2344 in Layer 5

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: 3.4816. Min Range: -3.4816

Max Act: 3.4816. Min Act: -0.1700

Data Index: 4700878 (Open Web Text)

Max Activating Token Index: 406

Text #1

Max Range: 3.4816. Min Range: -3.4816

Max Act: 3.3466. Min Act: -0.1700

Data Index: 142328 (Open Web Text)

Max Activating Token Index: 535

Text #2

Max Range: 3.4816. Min Range: -3.4816

Max Act: 3.3138. Min Act: -0.1700

Data Index: 6863793 (Open Web Text)

Max Activating Token Index: 195

Text #3

Max Range: 3.4816. Min Range: -3.4816

Max Act: 3.3063. Min Act: -0.1700

Data Index: 1511235 (Open Web Text)

Max Activating Token Index: 698

Text #4

Max Range: 3.4816. Min Range: -3.4816

Max Act: 3.3101. Min Act: -0.1700

Data Index: 7986897 (Open Web Text)

Max Activating Token Index: 504

Text #5

Max Range: 3.4816. Min Range: -3.4816

Max Act: 3.3121. Min Act: -0.1700

Data Index: 1420054 (Open Web Text)

Max Activating Token Index: 357

Text #6

Max Range: 3.4816. Min Range: -3.4816

Max Act: 3.2827. Min Act: -0.1700

Data Index: 3726658 (Open Web Text)

Max Activating Token Index: 951

Text #7

Max Range: 3.4816. Min Range: -3.4816

Max Act: 3.2981. Min Act: -0.1700

Data Index: 3950584 (Open Web Text)

Max Activating Token Index: 130

Text #8

Max Range: 3.4816. Min Range: -3.4816

Max Act: 3.2609. Min Act: -0.1700

Data Index: 6698517 (Open Web Text)

Max Activating Token Index: 858

Text #9

Max Range: 3.4816. Min Range: -3.4816

Max Act: 3.2765. Min Act: -0.1700

Data Index: 774337 (Open Web Text)

Max Activating Token Index: 171

Text #10

Max Range: 3.4816. Min Range: -3.4816

Max Act: 3.2355. Min Act: -0.1700

Data Index: 5257788 (Open Web Text)

Max Activating Token Index: 981

Text #11

Max Range: 3.4816. Min Range: -3.4816

Max Act: 3.2271. Min Act: -0.1700

Data Index: 6325096 (Open Web Text)

Max Activating Token Index: 676

Text #12

Max Range: 3.4816. Min Range: -3.4816

Max Act: 3.2204. Min Act: -0.1700

Data Index: 4357943 (Open Web Text)

Max Activating Token Index: 693

Text #13

Max Range: 3.4816. Min Range: -3.4816

Max Act: 3.2305. Min Act: -0.1700

Data Index: 2719281 (Open Web Text)

Max Activating Token Index: 602

Text #14

Max Range: 3.4816. Min Range: -3.4816

Max Act: 3.2168. Min Act: -0.1700

Data Index: 5122238 (Open Web Text)

Max Activating Token Index: 776

Text #15

Max Range: 3.4816. Min Range: -3.4816

Max Act: 3.2272. Min Act: -0.1700

Data Index: 1171895 (Open Web Text)

Max Activating Token Index: 337

Text #16

Max Range: 3.4816. Min Range: -3.4816

Max Act: 3.2153. Min Act: -0.1700

Data Index: 2544209 (Open Web Text)

Max Activating Token Index: 870

Text #17

Max Range: 3.4816. Min Range: -3.4816

Max Act: 3.2421. Min Act: -0.1700

Data Index: 437138 (Open Web Text)

Max Activating Token Index: 749

Text #18

Max Range: 3.4816. Min Range: -3.4816

Max Act: 3.2189. Min Act: -0.1700

Data Index: 7140438 (Open Web Text)

Max Activating Token Index: 571

Text #19

Max Range: 3.4816. Min Range: -3.4816

Max Act: 3.2185. Min Act: -0.1700

Data Index: 747472 (Open Web Text)

Max Activating Token Index: 872