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

Dataset: Open Web Text

Neuron 294 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: 4.8546. Min Range: -4.8546

Max Act: 4.8546. Min Act: -0.1700

Data Index: 5835440 (Open Web Text)

Max Activating Token Index: 721

Text #1

Max Range: 4.8546. Min Range: -4.8546

Max Act: 4.7428. Min Act: -0.1700

Data Index: 2323626 (Open Web Text)

Max Activating Token Index: 890

Text #2

Max Range: 4.8546. Min Range: -4.8546

Max Act: 4.7944. Min Act: -0.1700

Data Index: 2685483 (Open Web Text)

Max Activating Token Index: 908

Text #3

Max Range: 4.8546. Min Range: -4.8546

Max Act: 4.8244. Min Act: -0.1700

Data Index: 6556303 (Open Web Text)

Max Activating Token Index: 279

Text #4

Max Range: 4.8546. Min Range: -4.8546

Max Act: 4.8081. Min Act: -0.1700

Data Index: 1037286 (Open Web Text)

Max Activating Token Index: 49

Text #5

Max Range: 4.8546. Min Range: -4.8546

Max Act: 4.8008. Min Act: -0.1700

Data Index: 6074193 (Open Web Text)

Max Activating Token Index: 313

Text #6

Max Range: 4.8546. Min Range: -4.8546

Max Act: 4.7775. Min Act: -0.1700

Data Index: 7127894 (Open Web Text)

Max Activating Token Index: 555

Text #7

Max Range: 4.8546. Min Range: -4.8546

Max Act: 4.7927. Min Act: -0.1700

Data Index: 6682505 (Open Web Text)

Max Activating Token Index: 269

Text #8

Max Range: 4.8546. Min Range: -4.8546

Max Act: 4.7804. Min Act: -0.1700

Data Index: 2959121 (Open Web Text)

Max Activating Token Index: 68

Text #9

Max Range: 4.8546. Min Range: -4.8546

Max Act: 4.7403. Min Act: -0.1700

Data Index: 1230733 (Open Web Text)

Max Activating Token Index: 931

Text #10

Max Range: 4.8546. Min Range: -4.8546

Max Act: 4.7394. Min Act: -0.1700

Data Index: 1031263 (Open Web Text)

Max Activating Token Index: 925

Text #11

Max Range: 4.8546. Min Range: -4.8546

Max Act: 4.7794. Min Act: -0.1700

Data Index: 224406 (Open Web Text)

Max Activating Token Index: 168

Text #12

Max Range: 4.8546. Min Range: -4.8546

Max Act: 4.7901. Min Act: -0.1700

Data Index: 5491447 (Open Web Text)

Max Activating Token Index: 407

Text #13

Max Range: 4.8546. Min Range: -4.8546

Max Act: 4.7663. Min Act: -0.1700

Data Index: 592915 (Open Web Text)

Max Activating Token Index: 472

Text #14

Max Range: 4.8546. Min Range: -4.8546

Max Act: 4.7547. Min Act: -0.1700

Data Index: 3682791 (Open Web Text)

Max Activating Token Index: 482

Text #15

Max Range: 4.8546. Min Range: -4.8546

Max Act: 4.7474. Min Act: -0.1700

Data Index: 5554514 (Open Web Text)

Max Activating Token Index: 838

Text #16

Max Range: 4.8546. Min Range: -4.8546

Max Act: 4.7080. Min Act: -0.1700

Data Index: 3968739 (Open Web Text)

Max Activating Token Index: 129

Text #17

Max Range: 4.8546. Min Range: -4.8546

Max Act: 4.7699. Min Act: -0.1700

Data Index: 2568951 (Open Web Text)

Max Activating Token Index: 948

Text #18

Max Range: 4.8546. Min Range: -4.8546

Max Act: 4.7154. Min Act: -0.1700

Data Index: 8101259 (Open Web Text)

Max Activating Token Index: 544

Text #19

Max Range: 4.8546. Min Range: -4.8546

Max Act: 4.7379. Min Act: -0.1700

Data Index: 5412352 (Open Web Text)

Max Activating Token Index: 339