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

Dataset: Open Web Text

Neuron 2394 in Layer 4

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: 4.6650. Min Range: -4.6650

Max Act: 4.6650. Min Act: -0.1700

Data Index: 7281201 (Open Web Text)

Max Activating Token Index: 548

Text #1

Max Range: 4.6650. Min Range: -4.6650

Max Act: 4.6310. Min Act: -0.1700

Data Index: 6468677 (Open Web Text)

Max Activating Token Index: 860

Text #2

Max Range: 4.6650. Min Range: -4.6650

Max Act: 4.6125. Min Act: -0.1700

Data Index: 7522032 (Open Web Text)

Max Activating Token Index: 431

Text #3

Max Range: 4.6650. Min Range: -4.6650

Max Act: 4.6377. Min Act: -0.1700

Data Index: 1626956 (Open Web Text)

Max Activating Token Index: 356

Text #4

Max Range: 4.6650. Min Range: -4.6650

Max Act: 4.6441. Min Act: -0.1700

Data Index: 5814209 (Open Web Text)

Max Activating Token Index: 726

Text #5

Max Range: 4.6650. Min Range: -4.6650

Max Act: 4.6229. Min Act: -0.1700

Data Index: 8340817 (Open Web Text)

Max Activating Token Index: 478

Text #6

Max Range: 4.6650. Min Range: -4.6650

Max Act: 4.6337. Min Act: -0.1700

Data Index: 3403682 (Open Web Text)

Max Activating Token Index: 611

Text #7

Max Range: 4.6650. Min Range: -4.6650

Max Act: 4.6505. Min Act: -0.1700

Data Index: 7301590 (Open Web Text)

Max Activating Token Index: 857

Text #8

Max Range: 4.6650. Min Range: -4.6650

Max Act: 4.5614. Min Act: -0.1700

Data Index: 7349844 (Open Web Text)

Max Activating Token Index: 243

Text #9

Max Range: 4.6650. Min Range: -4.6650

Max Act: 4.5718. Min Act: -0.1700

Data Index: 5020630 (Open Web Text)

Max Activating Token Index: 452

Text #10

Max Range: 4.6650. Min Range: -4.6650

Max Act: 4.5589. Min Act: -0.1700

Data Index: 4877726 (Open Web Text)

Max Activating Token Index: 910

Text #11

Max Range: 4.6650. Min Range: -4.6650

Max Act: 4.5606. Min Act: -0.1700

Data Index: 830247 (Open Web Text)

Max Activating Token Index: 300

Text #12

Max Range: 4.6650. Min Range: -4.6650

Max Act: 4.5843. Min Act: -0.1700

Data Index: 7020996 (Open Web Text)

Max Activating Token Index: 75

Text #13

Max Range: 4.6650. Min Range: -4.6650

Max Act: 4.5764. Min Act: -0.1700

Data Index: 6995985 (Open Web Text)

Max Activating Token Index: 799

Text #14

Max Range: 4.6650. Min Range: -4.6650

Max Act: 4.5829. Min Act: -0.1700

Data Index: 8414663 (Open Web Text)

Max Activating Token Index: 963

Text #15

Max Range: 4.6650. Min Range: -4.6650

Max Act: 4.5788. Min Act: -0.1700

Data Index: 2980631 (Open Web Text)

Max Activating Token Index: 857

Text #16

Max Range: 4.6650. Min Range: -4.6650

Max Act: 4.5456. Min Act: -0.1700

Data Index: 2420304 (Open Web Text)

Max Activating Token Index: 881

Text #17

Max Range: 4.6650. Min Range: -4.6650

Max Act: 4.5079. Min Act: -0.1700

Data Index: 1022645 (Open Web Text)

Max Activating Token Index: 258

Text #18

Max Range: 4.6650. Min Range: -4.6650

Max Act: 4.5464. Min Act: -0.1700

Data Index: 4576470 (Open Web Text)

Max Activating Token Index: 769

Text #19

Max Range: 4.6650. Min Range: -4.6650

Max Act: 4.5457. Min Act: -0.1700

Data Index: 3997110 (Open Web Text)

Max Activating Token Index: 40