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

Dataset: Open Web Text

Neuron 2034 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: 7.1389. Min Range: -7.1389

Max Act: 7.1389. Min Act: -0.1700

Data Index: 3921258 (Open Web Text)

Max Activating Token Index: 770

Text #1

Max Range: 7.1389. Min Range: -7.1389

Max Act: 6.8859. Min Act: -0.1700

Data Index: 6643547 (Open Web Text)

Max Activating Token Index: 582

Text #2

Max Range: 7.1389. Min Range: -7.1389

Max Act: 6.7004. Min Act: -0.1700

Data Index: 312538 (Open Web Text)

Max Activating Token Index: 108

Text #3

Max Range: 7.1389. Min Range: -7.1389

Max Act: 6.7448. Min Act: -0.1700

Data Index: 8190460 (Open Web Text)

Max Activating Token Index: 515

Text #4

Max Range: 7.1389. Min Range: -7.1389

Max Act: 6.6756. Min Act: -0.1700

Data Index: 1954125 (Open Web Text)

Max Activating Token Index: 320

Text #5

Max Range: 7.1389. Min Range: -7.1389

Max Act: 6.6442. Min Act: -0.1700

Data Index: 5556970 (Open Web Text)

Max Activating Token Index: 913

Text #6

Max Range: 7.1389. Min Range: -7.1389

Max Act: 6.6198. Min Act: -0.1700

Data Index: 1113800 (Open Web Text)

Max Activating Token Index: 649

Text #7

Max Range: 7.1389. Min Range: -7.1389

Max Act: 6.6079. Min Act: -0.1700

Data Index: 1606521 (Open Web Text)

Max Activating Token Index: 887

Text #8

Max Range: 7.1389. Min Range: -7.1389

Max Act: 6.6314. Min Act: -0.1700

Data Index: 6165345 (Open Web Text)

Max Activating Token Index: 788

Text #9

Max Range: 7.1389. Min Range: -7.1389

Max Act: 6.5840. Min Act: -0.1700

Data Index: 7706427 (Open Web Text)

Max Activating Token Index: 415

Text #10

Max Range: 7.1389. Min Range: -7.1389

Max Act: 6.5606. Min Act: -0.1700

Data Index: 2617623 (Open Web Text)

Max Activating Token Index: 612

Text #11

Max Range: 7.1389. Min Range: -7.1389

Max Act: 6.6181. Min Act: -0.1700

Data Index: 1470798 (Open Web Text)

Max Activating Token Index: 514

Text #12

Max Range: 7.1389. Min Range: -7.1389

Max Act: 6.6301. Min Act: -0.1700

Data Index: 6031858 (Open Web Text)

Max Activating Token Index: 395

Text #13

Max Range: 7.1389. Min Range: -7.1389

Max Act: 6.5780. Min Act: -0.1700

Data Index: 731459 (Open Web Text)

Max Activating Token Index: 519

Text #14

Max Range: 7.1389. Min Range: -7.1389

Max Act: 6.6132. Min Act: -0.1700

Data Index: 1491269 (Open Web Text)

Max Activating Token Index: 391

Text #15

Max Range: 7.1389. Min Range: -7.1389

Max Act: 6.5654. Min Act: -0.1700

Data Index: 5193442 (Open Web Text)

Max Activating Token Index: 151

Text #16

Max Range: 7.1389. Min Range: -7.1389

Max Act: 6.5937. Min Act: -0.1700

Data Index: 7054935 (Open Web Text)

Max Activating Token Index: 449

Text #17

Max Range: 7.1389. Min Range: -7.1389

Max Act: 6.5752. Min Act: -0.1700

Data Index: 1311716 (Open Web Text)

Max Activating Token Index: 730

Text #18

Max Range: 7.1389. Min Range: -7.1389

Max Act: 6.5837. Min Act: -0.1700

Data Index: 7984207 (Open Web Text)

Max Activating Token Index: 277

Text #19

Max Range: 7.1389. Min Range: -7.1389

Max Act: 6.5347. Min Act: -0.1700

Data Index: 8320350 (Open Web Text)

Max Activating Token Index: 196