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

Dataset: Open Web Text

Neuron 2917 in Layer 5

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: 4.4286. Min Range: -4.4286

Max Act: 4.4286. Min Act: -0.1700

Data Index: 2678517 (Open Web Text)

Max Activating Token Index: 439

Text #1

Max Range: 4.4286. Min Range: -4.4286

Max Act: 4.3832. Min Act: -0.1700

Data Index: 6507964 (Open Web Text)

Max Activating Token Index: 494

Text #2

Max Range: 4.4286. Min Range: -4.4286

Max Act: 4.3187. Min Act: -0.1700

Data Index: 3832034 (Open Web Text)

Max Activating Token Index: 947

Text #3

Max Range: 4.4286. Min Range: -4.4286

Max Act: 4.3483. Min Act: -0.1700

Data Index: 5407388 (Open Web Text)

Max Activating Token Index: 447

Text #4

Max Range: 4.4286. Min Range: -4.4286

Max Act: 4.2793. Min Act: -0.1700

Data Index: 4871160 (Open Web Text)

Max Activating Token Index: 546

Text #5

Max Range: 4.4286. Min Range: -4.4286

Max Act: 4.2351. Min Act: -0.1700

Data Index: 3298125 (Open Web Text)

Max Activating Token Index: 212

Text #6

Max Range: 4.4286. Min Range: -4.4286

Max Act: 4.2222. Min Act: -0.1700

Data Index: 7697003 (Open Web Text)

Max Activating Token Index: 855

Text #7

Max Range: 4.4286. Min Range: -4.4286

Max Act: 4.2688. Min Act: -0.1700

Data Index: 967916 (Open Web Text)

Max Activating Token Index: 462

Text #8

Max Range: 4.4286. Min Range: -4.4286

Max Act: 4.2141. Min Act: -0.1700

Data Index: 6713319 (Open Web Text)

Max Activating Token Index: 963

Text #9

Max Range: 4.4286. Min Range: -4.4286

Max Act: 4.2156. Min Act: -0.1700

Data Index: 5834171 (Open Web Text)

Max Activating Token Index: 542

Text #10

Max Range: 4.4286. Min Range: -4.4286

Max Act: 4.1724. Min Act: -0.1700

Data Index: 6867535 (Open Web Text)

Max Activating Token Index: 901

Text #11

Max Range: 4.4286. Min Range: -4.4286

Max Act: 4.1813. Min Act: -0.1700

Data Index: 1478924 (Open Web Text)

Max Activating Token Index: 744

Text #12

Max Range: 4.4286. Min Range: -4.4286

Max Act: 4.1471. Min Act: -0.1700

Data Index: 1019989 (Open Web Text)

Max Activating Token Index: 993

Text #13

Max Range: 4.4286. Min Range: -4.4286

Max Act: 4.1453. Min Act: -0.1700

Data Index: 8167571 (Open Web Text)

Max Activating Token Index: 1006

Text #14

Max Range: 4.4286. Min Range: -4.4286

Max Act: 4.1663. Min Act: -0.1700

Data Index: 1785290 (Open Web Text)

Max Activating Token Index: 595

Text #15

Max Range: 4.4286. Min Range: -4.4286

Max Act: 4.1374. Min Act: -0.1700

Data Index: 3614535 (Open Web Text)

Max Activating Token Index: 294

Text #16

Max Range: 4.4286. Min Range: -4.4286

Max Act: 4.1430. Min Act: -0.1700

Data Index: 7581619 (Open Web Text)

Max Activating Token Index: 131

Text #17

Max Range: 4.4286. Min Range: -4.4286

Max Act: 4.1620. Min Act: -0.1700

Data Index: 2020931 (Open Web Text)

Max Activating Token Index: 956

Text #18

Max Range: 4.4286. Min Range: -4.4286

Max Act: 4.1814. Min Act: -0.1700

Data Index: 1433266 (Open Web Text)

Max Activating Token Index: 467

Text #19

Max Range: 4.4286. Min Range: -4.4286

Max Act: 4.1619. Min Act: -0.1700

Data Index: 5301911 (Open Web Text)

Max Activating Token Index: 804