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

Dataset: Open Web Text

Neuron 512 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: 1.5110. Min Range: -1.5110

Max Act: 1.5076. Min Act: -0.1558

Data Index: 4546881 (Open Web Text)

Max Activating Token Index: 128

Text #1

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.5110. Min Act: -0.1699

Data Index: 8386324 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.4885. Min Act: -0.1700

Data Index: 5702967 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.4876. Min Act: -0.1697

Data Index: 7859403 (Open Web Text)

Max Activating Token Index: 695

Text #4

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.4765. Min Act: -0.1698

Data Index: 4652151 (Open Web Text)

Max Activating Token Index: 123

Text #5

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.4561. Min Act: -0.1697

Data Index: 1720095 (Open Web Text)

Max Activating Token Index: 417

Text #6

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.4513. Min Act: -0.1598

Data Index: 6412893 (Open Web Text)

Max Activating Token Index: 129

Text #7

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.4464. Min Act: -0.1581

Data Index: 7134362 (Open Web Text)

Max Activating Token Index: 544

Text #8

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.4516. Min Act: -0.1691

Data Index: 3992793 (Open Web Text)

Max Activating Token Index: 51

Text #9

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.4574. Min Act: -0.1518

Data Index: 2092837 (Open Web Text)

Max Activating Token Index: 882

Text #10

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.4477. Min Act: -0.1578

Data Index: 4206956 (Open Web Text)

Max Activating Token Index: 931

Text #11

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.4422. Min Act: -0.1683

Data Index: 7303465 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.4378. Min Act: -0.1556

Data Index: 2568119 (Open Web Text)

Max Activating Token Index: 225

Text #13

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.4359. Min Act: -0.1691

Data Index: 3451650 (Open Web Text)

Max Activating Token Index: 114

Text #14

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.4265. Min Act: -0.1700

Data Index: 2854310 (Open Web Text)

Max Activating Token Index: 33

Text #15

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.4272. Min Act: -0.1700

Data Index: 4446678 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.4272. Min Act: -0.1678

Data Index: 607863 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.4284. Min Act: -0.1675

Data Index: 3992792 (Open Web Text)

Max Activating Token Index: 270

Text #18

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.4270. Min Act: -0.1698

Data Index: 26093 (Open Web Text)

Max Activating Token Index: 26

Text #19

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.4272. Min Act: -0.1700

Data Index: 1168471 (Open Web Text)

Max Activating Token Index: 2