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

Dataset: Open Web Text

Neuron 1550 in Layer 0

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: 2.9377. Min Range: -2.9377

Max Act: 2.9377. Min Act: -0.1700

Data Index: 7374078 (Open Web Text)

Max Activating Token Index: 337

Text #1

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.9303. Min Act: -0.1700

Data Index: 3510649 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.9106. Min Act: -0.1700

Data Index: 1053983 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.9072. Min Act: -0.1700

Data Index: 4361051 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.9032. Min Act: -0.1700

Data Index: 8190863 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8852. Min Act: -0.1700

Data Index: 4209725 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8862. Min Act: -0.1700

Data Index: 635645 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8821. Min Act: -0.1700

Data Index: 1926069 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8672. Min Act: -0.1700

Data Index: 3412009 (Open Web Text)

Max Activating Token Index: 769

Text #9

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8611. Min Act: -0.1700

Data Index: 6106533 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8611. Min Act: -0.1700

Data Index: 3574418 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8611. Min Act: -0.1700

Data Index: 2199640 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8518. Min Act: -0.1700

Data Index: 6516373 (Open Web Text)

Max Activating Token Index: 558

Text #13

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8382. Min Act: -0.1700

Data Index: 8451788 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8310. Min Act: -0.1700

Data Index: 7950097 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8150. Min Act: -0.1700

Data Index: 7234985 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8285. Min Act: -0.1700

Data Index: 277065 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8105. Min Act: -0.1700

Data Index: 1671544 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8046. Min Act: -0.1700

Data Index: 903188 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8105. Min Act: -0.1700

Data Index: 979024 (Open Web Text)

Max Activating Token Index: 2