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

Dataset: Open Web Text

Neuron 2118 in Layer 6

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: 3.0508. Min Range: -3.0508

Max Act: 3.0508. Min Act: -0.1700

Data Index: 2624016 (Open Web Text)

Max Activating Token Index: 242

Text #1

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9727. Min Act: -0.1700

Data Index: 3747591 (Open Web Text)

Max Activating Token Index: 169

Text #2

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9856. Min Act: -0.1700

Data Index: 7618097 (Open Web Text)

Max Activating Token Index: 583

Text #3

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9612. Min Act: -0.1700

Data Index: 4893092 (Open Web Text)

Max Activating Token Index: 202

Text #4

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9503. Min Act: -0.1700

Data Index: 951841 (Open Web Text)

Max Activating Token Index: 546

Text #5

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9350. Min Act: -0.1700

Data Index: 7723795 (Open Web Text)

Max Activating Token Index: 898

Text #6

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9625. Min Act: -0.1700

Data Index: 1448787 (Open Web Text)

Max Activating Token Index: 487

Text #7

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9262. Min Act: -0.1700

Data Index: 492460 (Open Web Text)

Max Activating Token Index: 599

Text #8

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9427. Min Act: -0.1700

Data Index: 6383166 (Open Web Text)

Max Activating Token Index: 327

Text #9

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9230. Min Act: -0.1700

Data Index: 752978 (Open Web Text)

Max Activating Token Index: 784

Text #10

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9161. Min Act: -0.1700

Data Index: 6098969 (Open Web Text)

Max Activating Token Index: 181

Text #11

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9205. Min Act: -0.1700

Data Index: 103027 (Open Web Text)

Max Activating Token Index: 231

Text #12

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.8973. Min Act: -0.1700

Data Index: 2536121 (Open Web Text)

Max Activating Token Index: 972

Text #13

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9068. Min Act: -0.1700

Data Index: 8181063 (Open Web Text)

Max Activating Token Index: 793

Text #14

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9036. Min Act: -0.1700

Data Index: 107750 (Open Web Text)

Max Activating Token Index: 980

Text #15

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9216. Min Act: -0.1700

Data Index: 1303937 (Open Web Text)

Max Activating Token Index: 102

Text #16

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9139. Min Act: -0.1700

Data Index: 5279462 (Open Web Text)

Max Activating Token Index: 425

Text #17

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9092. Min Act: -0.1700

Data Index: 8697323 (Open Web Text)

Max Activating Token Index: 255

Text #18

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.9080. Min Act: -0.1700

Data Index: 2516482 (Open Web Text)

Max Activating Token Index: 607

Text #19

Max Range: 3.0508. Min Range: -3.0508

Max Act: 2.8699. Min Act: -0.1700

Data Index: 2726127 (Open Web Text)

Max Activating Token Index: 207