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

Dataset: Open Web Text

Neuron 1438 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: 1.3006. Min Range: -1.3006

Max Act: 1.3006. Min Act: -0.1643

Data Index: 4231544 (Open Web Text)

Max Activating Token Index: 583

Text #1

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2887. Min Act: -0.1608

Data Index: 5165105 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2736. Min Act: -0.1692

Data Index: 6565716 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2613. Min Act: -0.1700

Data Index: 346513 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2436. Min Act: -0.1621

Data Index: 4858033 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2394. Min Act: -0.1670

Data Index: 204682 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2350. Min Act: -0.1700

Data Index: 3855217 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2364. Min Act: -0.1699

Data Index: 4608679 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2260. Min Act: -0.1683

Data Index: 4661122 (Open Web Text)

Max Activating Token Index: 62

Text #9

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2100. Min Act: -0.1700

Data Index: 7203224 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2044. Min Act: -0.1681

Data Index: 2838986 (Open Web Text)

Max Activating Token Index: 234

Text #11

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2119. Min Act: -0.1700

Data Index: 4090283 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2175. Min Act: -0.1700

Data Index: 4052388 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2037. Min Act: -0.1687

Data Index: 538893 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2093. Min Act: -0.1652

Data Index: 862944 (Open Web Text)

Max Activating Token Index: 15

Text #15

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2044. Min Act: -0.1700

Data Index: 3260657 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2032. Min Act: -0.1700

Data Index: 3559691 (Open Web Text)

Max Activating Token Index: 39

Text #17

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2018. Min Act: -0.1689

Data Index: 7793734 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.1944. Min Act: -0.1700

Data Index: 4875906 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.1955. Min Act: -0.1609

Data Index: 2765172 (Open Web Text)

Max Activating Token Index: 3