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

Dataset: Open Web Text

Neuron 1839 in Layer 1

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: 2.0044. Min Range: -2.0044

Max Act: 2.0044. Min Act: -0.1700

Data Index: 3085739 (Open Web Text)

Max Activating Token Index: 83

Text #1

Max Range: 2.0044. Min Range: -2.0044

Max Act: 2.0023. Min Act: -0.1615

Data Index: 956612 (Open Web Text)

Max Activating Token Index: 194

Text #2

Max Range: 2.0044. Min Range: -2.0044

Max Act: 2.0021. Min Act: -0.1700

Data Index: 3231067 (Open Web Text)

Max Activating Token Index: 673

Text #3

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.9990. Min Act: -0.1699

Data Index: 7208225 (Open Web Text)

Max Activating Token Index: 1011

Text #4

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.9647. Min Act: -0.1700

Data Index: 6701506 (Open Web Text)

Max Activating Token Index: 32

Text #5

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.9484. Min Act: -0.1700

Data Index: 4724674 (Open Web Text)

Max Activating Token Index: 194

Text #6

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.9490. Min Act: -0.1691

Data Index: 3552857 (Open Web Text)

Max Activating Token Index: 38

Text #7

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.9435. Min Act: -0.1683

Data Index: 1013245 (Open Web Text)

Max Activating Token Index: 219

Text #8

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.9316. Min Act: -0.1700

Data Index: 4843018 (Open Web Text)

Max Activating Token Index: 113

Text #9

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.9349. Min Act: -0.1700

Data Index: 465693 (Open Web Text)

Max Activating Token Index: 395

Text #10

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.9244. Min Act: -0.1700

Data Index: 8412208 (Open Web Text)

Max Activating Token Index: 553

Text #11

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.9244. Min Act: -0.1699

Data Index: 5770601 (Open Web Text)

Max Activating Token Index: 43

Text #12

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.9138. Min Act: -0.1686

Data Index: 2226054 (Open Web Text)

Max Activating Token Index: 26

Text #13

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.9061. Min Act: -0.1700

Data Index: 5757689 (Open Web Text)

Max Activating Token Index: 738

Text #14

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.9100. Min Act: -0.1696

Data Index: 5629005 (Open Web Text)

Max Activating Token Index: 480

Text #15

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.9124. Min Act: -0.1662

Data Index: 5227696 (Open Web Text)

Max Activating Token Index: 895

Text #16

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.9142. Min Act: -0.1700

Data Index: 8314477 (Open Web Text)

Max Activating Token Index: 66

Text #17

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.9104. Min Act: -0.1700

Data Index: 3489514 (Open Web Text)

Max Activating Token Index: 419

Text #18

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.9143. Min Act: -0.1700

Data Index: 4936573 (Open Web Text)

Max Activating Token Index: 391

Text #19

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.9082. Min Act: -0.1700

Data Index: 1547093 (Open Web Text)

Max Activating Token Index: 23