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

Dataset: Open Web Text

Neuron 1376 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: 4.3788. Min Range: -4.3788

Max Act: 4.3788. Min Act: -0.1700

Data Index: 1184907 (Open Web Text)

Max Activating Token Index: 734

Text #1

Max Range: 4.3788. Min Range: -4.3788

Max Act: 4.3013. Min Act: -0.1700

Data Index: 727684 (Open Web Text)

Max Activating Token Index: 621

Text #2

Max Range: 4.3788. Min Range: -4.3788

Max Act: 4.2887. Min Act: -0.1700

Data Index: 5291436 (Open Web Text)

Max Activating Token Index: 677

Text #3

Max Range: 4.3788. Min Range: -4.3788

Max Act: 4.3127. Min Act: -0.1700

Data Index: 1437159 (Open Web Text)

Max Activating Token Index: 370

Text #4

Max Range: 4.3788. Min Range: -4.3788

Max Act: 4.3196. Min Act: -0.1700

Data Index: 1448234 (Open Web Text)

Max Activating Token Index: 516

Text #5

Max Range: 4.3788. Min Range: -4.3788

Max Act: 4.2207. Min Act: -0.1700

Data Index: 5324630 (Open Web Text)

Max Activating Token Index: 137

Text #6

Max Range: 4.3788. Min Range: -4.3788

Max Act: 4.2655. Min Act: -0.1700

Data Index: 3638276 (Open Web Text)

Max Activating Token Index: 866

Text #7

Max Range: 4.3788. Min Range: -4.3788

Max Act: 4.1996. Min Act: -0.1700

Data Index: 1377368 (Open Web Text)

Max Activating Token Index: 185

Text #8

Max Range: 4.3788. Min Range: -4.3788

Max Act: 4.2092. Min Act: -0.1700

Data Index: 4713452 (Open Web Text)

Max Activating Token Index: 777

Text #9

Max Range: 4.3788. Min Range: -4.3788

Max Act: 4.2247. Min Act: -0.1700

Data Index: 3634154 (Open Web Text)

Max Activating Token Index: 180

Text #10

Max Range: 4.3788. Min Range: -4.3788

Max Act: 4.2247. Min Act: -0.1700

Data Index: 7237437 (Open Web Text)

Max Activating Token Index: 671

Text #11

Max Range: 4.3788. Min Range: -4.3788

Max Act: 4.2300. Min Act: -0.1700

Data Index: 3924512 (Open Web Text)

Max Activating Token Index: 255

Text #12

Max Range: 4.3788. Min Range: -4.3788

Max Act: 4.2218. Min Act: -0.1700

Data Index: 232914 (Open Web Text)

Max Activating Token Index: 896

Text #13

Max Range: 4.3788. Min Range: -4.3788

Max Act: 4.2119. Min Act: -0.1700

Data Index: 7499542 (Open Web Text)

Max Activating Token Index: 236

Text #14

Max Range: 4.3788. Min Range: -4.3788

Max Act: 4.1575. Min Act: -0.1700

Data Index: 510555 (Open Web Text)

Max Activating Token Index: 411

Text #15

Max Range: 4.3788. Min Range: -4.3788

Max Act: 4.1564. Min Act: -0.1700

Data Index: 1674216 (Open Web Text)

Max Activating Token Index: 481

Text #16

Max Range: 4.3788. Min Range: -4.3788

Max Act: 4.1348. Min Act: -0.1700

Data Index: 6103527 (Open Web Text)

Max Activating Token Index: 826

Text #17

Max Range: 4.3788. Min Range: -4.3788

Max Act: 4.1253. Min Act: -0.1700

Data Index: 6030613 (Open Web Text)

Max Activating Token Index: 730

Text #18

Max Range: 4.3788. Min Range: -4.3788

Max Act: 4.1598. Min Act: -0.1700

Data Index: 4468207 (Open Web Text)

Max Activating Token Index: 763

Text #19

Max Range: 4.3788. Min Range: -4.3788

Max Act: 4.1760. Min Act: -0.1700

Data Index: 4523951 (Open Web Text)

Max Activating Token Index: 830