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

Dataset: Open Web Text

Neuron 1945 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: 3.8313. Min Range: -3.8313

Max Act: 3.8313. Min Act: -0.1700

Data Index: 1135999 (Open Web Text)

Max Activating Token Index: 697

Text #1

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.8300. Min Act: -0.1700

Data Index: 3065460 (Open Web Text)

Max Activating Token Index: 137

Text #2

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.8106. Min Act: -0.1700

Data Index: 1007622 (Open Web Text)

Max Activating Token Index: 647

Text #3

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.8049. Min Act: -0.1700

Data Index: 6834329 (Open Web Text)

Max Activating Token Index: 787

Text #4

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.7590. Min Act: -0.1700

Data Index: 1126167 (Open Web Text)

Max Activating Token Index: 531

Text #5

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.7397. Min Act: -0.1700

Data Index: 3547834 (Open Web Text)

Max Activating Token Index: 293

Text #6

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.7009. Min Act: -0.1700

Data Index: 6512880 (Open Web Text)

Max Activating Token Index: 727

Text #7

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6914. Min Act: -0.1700

Data Index: 4799622 (Open Web Text)

Max Activating Token Index: 643

Text #8

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.7444. Min Act: -0.1700

Data Index: 7608685 (Open Web Text)

Max Activating Token Index: 154

Text #9

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6927. Min Act: -0.1700

Data Index: 6512881 (Open Web Text)

Max Activating Token Index: 374

Text #10

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6944. Min Act: -0.1700

Data Index: 292006 (Open Web Text)

Max Activating Token Index: 773

Text #11

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6659. Min Act: -0.1700

Data Index: 7417701 (Open Web Text)

Max Activating Token Index: 768

Text #12

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.7203. Min Act: -0.1700

Data Index: 1077057 (Open Web Text)

Max Activating Token Index: 430

Text #13

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6584. Min Act: -0.1700

Data Index: 5988926 (Open Web Text)

Max Activating Token Index: 915

Text #14

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6525. Min Act: -0.1700

Data Index: 6312604 (Open Web Text)

Max Activating Token Index: 282

Text #15

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6947. Min Act: -0.1700

Data Index: 629520 (Open Web Text)

Max Activating Token Index: 721

Text #16

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.7020. Min Act: -0.1700

Data Index: 4120214 (Open Web Text)

Max Activating Token Index: 560

Text #17

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6591. Min Act: -0.1700

Data Index: 1210398 (Open Web Text)

Max Activating Token Index: 691

Text #18

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6428. Min Act: -0.1700

Data Index: 1480070 (Open Web Text)

Max Activating Token Index: 710

Text #19

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6632. Min Act: -0.1700

Data Index: 6512879 (Open Web Text)

Max Activating Token Index: 73