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

Dataset: Open Web Text

Neuron 2129 in Layer 2

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: 3.2866. Min Range: -3.2866

Max Act: 3.2773. Min Act: -0.1700

Data Index: 8686403 (Open Web Text)

Max Activating Token Index: 944

Text #1

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.2866. Min Act: -0.1700

Data Index: 6779406 (Open Web Text)

Max Activating Token Index: 469

Text #2

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.2509. Min Act: -0.1700

Data Index: 2484166 (Open Web Text)

Max Activating Token Index: 430

Text #3

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.2398. Min Act: -0.1700

Data Index: 5369353 (Open Web Text)

Max Activating Token Index: 937

Text #4

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.2092. Min Act: -0.1700

Data Index: 2094558 (Open Web Text)

Max Activating Token Index: 578

Text #5

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.2348. Min Act: -0.1700

Data Index: 1917846 (Open Web Text)

Max Activating Token Index: 460

Text #6

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1927. Min Act: -0.1700

Data Index: 7644733 (Open Web Text)

Max Activating Token Index: 793

Text #7

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.2187. Min Act: -0.1700

Data Index: 1538569 (Open Web Text)

Max Activating Token Index: 711

Text #8

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1896. Min Act: -0.1700

Data Index: 2470363 (Open Web Text)

Max Activating Token Index: 585

Text #9

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1912. Min Act: -0.1700

Data Index: 3243168 (Open Web Text)

Max Activating Token Index: 233

Text #10

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1851. Min Act: -0.1700

Data Index: 7226319 (Open Web Text)

Max Activating Token Index: 711

Text #11

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1538. Min Act: -0.1700

Data Index: 1828074 (Open Web Text)

Max Activating Token Index: 285

Text #12

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1259. Min Act: -0.1700

Data Index: 3977075 (Open Web Text)

Max Activating Token Index: 210

Text #13

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1403. Min Act: -0.1700

Data Index: 2538120 (Open Web Text)

Max Activating Token Index: 518

Text #14

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1326. Min Act: -0.1700

Data Index: 2350217 (Open Web Text)

Max Activating Token Index: 113

Text #15

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1822. Min Act: -0.1700

Data Index: 6880891 (Open Web Text)

Max Activating Token Index: 467

Text #16

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1763. Min Act: -0.1700

Data Index: 7370186 (Open Web Text)

Max Activating Token Index: 285

Text #17

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1447. Min Act: -0.1700

Data Index: 8123503 (Open Web Text)

Max Activating Token Index: 216

Text #18

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.0987. Min Act: -0.1700

Data Index: 3042079 (Open Web Text)

Max Activating Token Index: 397

Text #19

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1050. Min Act: -0.1700

Data Index: 4939171 (Open Web Text)

Max Activating Token Index: 601