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

Dataset: Open Web Text

Neuron 1326 in Layer 2

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: 5.0077. Min Range: -5.0077

Max Act: 5.0077. Min Act: -0.1700

Data Index: 1790363 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.9760. Min Act: -0.1700

Data Index: 5083621 (Open Web Text)

Max Activating Token Index: 22

Text #2

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.8360. Min Act: -0.1700

Data Index: 3759168 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.8310. Min Act: -0.1700

Data Index: 7930993 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.7877. Min Act: -0.1700

Data Index: 3404174 (Open Web Text)

Max Activating Token Index: 751

Text #5

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.7799. Min Act: -0.1700

Data Index: 6854526 (Open Web Text)

Max Activating Token Index: 23

Text #6

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.7890. Min Act: -0.1700

Data Index: 2920948 (Open Web Text)

Max Activating Token Index: 650

Text #7

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.7484. Min Act: -0.1700

Data Index: 805618 (Open Web Text)

Max Activating Token Index: 653

Text #8

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.7441. Min Act: -0.1700

Data Index: 5518060 (Open Web Text)

Max Activating Token Index: 664

Text #9

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.7627. Min Act: -0.1700

Data Index: 7887166 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.7312. Min Act: -0.1700

Data Index: 2246563 (Open Web Text)

Max Activating Token Index: 207

Text #11

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.7055. Min Act: -0.1700

Data Index: 3746527 (Open Web Text)

Max Activating Token Index: 271

Text #12

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.7203. Min Act: -0.1700

Data Index: 38548 (Open Web Text)

Max Activating Token Index: 62

Text #13

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.7086. Min Act: -0.1700

Data Index: 3929828 (Open Web Text)

Max Activating Token Index: 101

Text #14

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.7124. Min Act: -0.1700

Data Index: 84210 (Open Web Text)

Max Activating Token Index: 112

Text #15

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.6783. Min Act: -0.1700

Data Index: 830434 (Open Web Text)

Max Activating Token Index: 31

Text #16

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.6763. Min Act: -0.1700

Data Index: 199563 (Open Web Text)

Max Activating Token Index: 46

Text #17

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.6672. Min Act: -0.1700

Data Index: 4218952 (Open Web Text)

Max Activating Token Index: 19

Text #18

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.6451. Min Act: -0.1700

Data Index: 3321145 (Open Web Text)

Max Activating Token Index: 238

Text #19

Max Range: 5.0077. Min Range: -5.0077

Max Act: 4.6315. Min Act: -0.1700

Data Index: 1586659 (Open Web Text)

Max Activating Token Index: 16