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

Dataset: Open Web Text

Neuron 1385 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: 3.2272. Min Range: -3.2272

Max Act: 3.2272. Min Act: -0.1700

Data Index: 7725099 (Open Web Text)

Max Activating Token Index: 598

Text #1

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.1597. Min Act: -0.1700

Data Index: 7041737 (Open Web Text)

Max Activating Token Index: 660

Text #2

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.1622. Min Act: -0.1700

Data Index: 918844 (Open Web Text)

Max Activating Token Index: 32

Text #3

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.1247. Min Act: -0.1700

Data Index: 7890329 (Open Web Text)

Max Activating Token Index: 707

Text #4

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.1286. Min Act: -0.1700

Data Index: 5080589 (Open Web Text)

Max Activating Token Index: 569

Text #5

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.0884. Min Act: -0.1700

Data Index: 4560669 (Open Web Text)

Max Activating Token Index: 859

Text #6

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.1011. Min Act: -0.1700

Data Index: 7134852 (Open Web Text)

Max Activating Token Index: 958

Text #7

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.1106. Min Act: -0.1700

Data Index: 7642274 (Open Web Text)

Max Activating Token Index: 646

Text #8

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.0903. Min Act: -0.1700

Data Index: 3490620 (Open Web Text)

Max Activating Token Index: 583

Text #9

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.0765. Min Act: -0.1700

Data Index: 4620408 (Open Web Text)

Max Activating Token Index: 893

Text #10

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.0532. Min Act: -0.1700

Data Index: 1591055 (Open Web Text)

Max Activating Token Index: 76

Text #11

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.0443. Min Act: -0.1700

Data Index: 1444466 (Open Web Text)

Max Activating Token Index: 281

Text #12

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.0567. Min Act: -0.1700

Data Index: 7833297 (Open Web Text)

Max Activating Token Index: 816

Text #13

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.0151. Min Act: -0.1700

Data Index: 2280428 (Open Web Text)

Max Activating Token Index: 196

Text #14

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.0176. Min Act: -0.1700

Data Index: 758855 (Open Web Text)

Max Activating Token Index: 512

Text #15

Max Range: 3.2272. Min Range: -3.2272

Max Act: 2.9923. Min Act: -0.1700

Data Index: 8457974 (Open Web Text)

Max Activating Token Index: 514

Text #16

Max Range: 3.2272. Min Range: -3.2272

Max Act: 2.9942. Min Act: -0.1700

Data Index: 2566689 (Open Web Text)

Max Activating Token Index: 224

Text #17

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.0002. Min Act: -0.1700

Data Index: 3158502 (Open Web Text)

Max Activating Token Index: 66

Text #18

Max Range: 3.2272. Min Range: -3.2272

Max Act: 2.9834. Min Act: -0.1700

Data Index: 45668 (Open Web Text)

Max Activating Token Index: 630

Text #19

Max Range: 3.2272. Min Range: -3.2272

Max Act: 2.9962. Min Act: -0.1700

Data Index: 2627404 (Open Web Text)

Max Activating Token Index: 78