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

Dataset: Open Web Text

Neuron 768 in Layer 6

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: 4.8873. Min Range: -4.8873

Max Act: 4.8873. Min Act: -0.1700

Data Index: 1145029 (Open Web Text)

Max Activating Token Index: 774

Text #1

Max Range: 4.8873. Min Range: -4.8873

Max Act: 4.7868. Min Act: -0.1700

Data Index: 102169 (Open Web Text)

Max Activating Token Index: 94

Text #2

Max Range: 4.8873. Min Range: -4.8873

Max Act: 4.7337. Min Act: -0.1700

Data Index: 3343725 (Open Web Text)

Max Activating Token Index: 150

Text #3

Max Range: 4.8873. Min Range: -4.8873

Max Act: 4.7432. Min Act: -0.1700

Data Index: 556469 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 4.8873. Min Range: -4.8873

Max Act: 4.7771. Min Act: -0.1700

Data Index: 6904388 (Open Web Text)

Max Activating Token Index: 53

Text #5

Max Range: 4.8873. Min Range: -4.8873

Max Act: 4.7171. Min Act: -0.1700

Data Index: 6309062 (Open Web Text)

Max Activating Token Index: 573

Text #6

Max Range: 4.8873. Min Range: -4.8873

Max Act: 4.6922. Min Act: -0.1700

Data Index: 4643040 (Open Web Text)

Max Activating Token Index: 256

Text #7

Max Range: 4.8873. Min Range: -4.8873

Max Act: 4.6838. Min Act: -0.1700

Data Index: 5660095 (Open Web Text)

Max Activating Token Index: 798

Text #8

Max Range: 4.8873. Min Range: -4.8873

Max Act: 4.6783. Min Act: -0.1700

Data Index: 3564313 (Open Web Text)

Max Activating Token Index: 359

Text #9

Max Range: 4.8873. Min Range: -4.8873

Max Act: 4.6681. Min Act: -0.1700

Data Index: 4216807 (Open Web Text)

Max Activating Token Index: 159

Text #10

Max Range: 4.8873. Min Range: -4.8873

Max Act: 4.6355. Min Act: -0.1700

Data Index: 448387 (Open Web Text)

Max Activating Token Index: 49

Text #11

Max Range: 4.8873. Min Range: -4.8873

Max Act: 4.6662. Min Act: -0.1700

Data Index: 3033897 (Open Web Text)

Max Activating Token Index: 295

Text #12

Max Range: 4.8873. Min Range: -4.8873

Max Act: 4.6512. Min Act: -0.1700

Data Index: 5784519 (Open Web Text)

Max Activating Token Index: 288

Text #13

Max Range: 4.8873. Min Range: -4.8873

Max Act: 4.6129. Min Act: -0.1700

Data Index: 556468 (Open Web Text)

Max Activating Token Index: 161

Text #14

Max Range: 4.8873. Min Range: -4.8873

Max Act: 4.6403. Min Act: -0.1700

Data Index: 5633672 (Open Web Text)

Max Activating Token Index: 131

Text #15

Max Range: 4.8873. Min Range: -4.8873

Max Act: 4.6601. Min Act: -0.1700

Data Index: 5453994 (Open Web Text)

Max Activating Token Index: 996

Text #16

Max Range: 4.8873. Min Range: -4.8873

Max Act: 4.5951. Min Act: -0.1700

Data Index: 970458 (Open Web Text)

Max Activating Token Index: 344

Text #17

Max Range: 4.8873. Min Range: -4.8873

Max Act: 4.6093. Min Act: -0.1700

Data Index: 2956867 (Open Web Text)

Max Activating Token Index: 330

Text #18

Max Range: 4.8873. Min Range: -4.8873

Max Act: 4.5999. Min Act: -0.1700

Data Index: 5162697 (Open Web Text)

Max Activating Token Index: 553

Text #19

Max Range: 4.8873. Min Range: -4.8873

Max Act: 4.6095. Min Act: -0.1700

Data Index: 3863601 (Open Web Text)

Max Activating Token Index: 412