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

Dataset: Open Web Text

Neuron 168 in Layer 1

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: 1.9375. Min Range: -1.9375

Max Act: 1.9375. Min Act: -0.1700

Data Index: 2200639 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.9375. Min Range: -1.9375

Max Act: 1.9042. Min Act: -0.1700

Data Index: 6167529 (Open Web Text)

Max Activating Token Index: 621

Text #2

Max Range: 1.9375. Min Range: -1.9375

Max Act: 1.9008. Min Act: -0.1700

Data Index: 5323156 (Open Web Text)

Max Activating Token Index: 641

Text #3

Max Range: 1.9375. Min Range: -1.9375

Max Act: 1.8834. Min Act: -0.1700

Data Index: 5257608 (Open Web Text)

Max Activating Token Index: 593

Text #4

Max Range: 1.9375. Min Range: -1.9375

Max Act: 1.8870. Min Act: -0.1700

Data Index: 6878629 (Open Web Text)

Max Activating Token Index: 139

Text #5

Max Range: 1.9375. Min Range: -1.9375

Max Act: 1.8644. Min Act: -0.1700

Data Index: 4456623 (Open Web Text)

Max Activating Token Index: 449

Text #6

Max Range: 1.9375. Min Range: -1.9375

Max Act: 1.8624. Min Act: -0.1640

Data Index: 1322532 (Open Web Text)

Max Activating Token Index: 972

Text #7

Max Range: 1.9375. Min Range: -1.9375

Max Act: 1.8653. Min Act: -0.1700

Data Index: 7493150 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 1.9375. Min Range: -1.9375

Max Act: 1.8560. Min Act: -0.1700

Data Index: 280342 (Open Web Text)

Max Activating Token Index: 554

Text #9

Max Range: 1.9375. Min Range: -1.9375

Max Act: 1.8629. Min Act: -0.1700

Data Index: 7571187 (Open Web Text)

Max Activating Token Index: 521

Text #10

Max Range: 1.9375. Min Range: -1.9375

Max Act: 1.8519. Min Act: -0.1700

Data Index: 2755491 (Open Web Text)

Max Activating Token Index: 253

Text #11

Max Range: 1.9375. Min Range: -1.9375

Max Act: 1.8392. Min Act: -0.1700

Data Index: 8790081 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 1.9375. Min Range: -1.9375

Max Act: 1.8431. Min Act: -0.1700

Data Index: 5253339 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 1.9375. Min Range: -1.9375

Max Act: 1.8440. Min Act: -0.1700

Data Index: 3707766 (Open Web Text)

Max Activating Token Index: 677

Text #14

Max Range: 1.9375. Min Range: -1.9375

Max Act: 1.8416. Min Act: -0.1700

Data Index: 170698 (Open Web Text)

Max Activating Token Index: 59

Text #15

Max Range: 1.9375. Min Range: -1.9375

Max Act: 1.8301. Min Act: -0.1699

Data Index: 172978 (Open Web Text)

Max Activating Token Index: 724

Text #16

Max Range: 1.9375. Min Range: -1.9375

Max Act: 1.8305. Min Act: -0.1700

Data Index: 689112 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 1.9375. Min Range: -1.9375

Max Act: 1.8247. Min Act: -0.1700

Data Index: 6792956 (Open Web Text)

Max Activating Token Index: 83

Text #18

Max Range: 1.9375. Min Range: -1.9375

Max Act: 1.8330. Min Act: -0.1700

Data Index: 8426626 (Open Web Text)

Max Activating Token Index: 583

Text #19

Max Range: 1.9375. Min Range: -1.9375

Max Act: 1.8046. Min Act: -0.1700

Data Index: 3375937 (Open Web Text)

Max Activating Token Index: 441