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

Dataset: Open Web Text

Neuron 503 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: 4.1234. Min Range: -4.1234

Max Act: 4.1234. Min Act: -0.1700

Data Index: 4052760 (Open Web Text)

Max Activating Token Index: 512

Text #1

Max Range: 4.1234. Min Range: -4.1234

Max Act: 4.0839. Min Act: -0.1700

Data Index: 7003883 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 4.1234. Min Range: -4.1234

Max Act: 4.0760. Min Act: -0.1700

Data Index: 221015 (Open Web Text)

Max Activating Token Index: 633

Text #3

Max Range: 4.1234. Min Range: -4.1234

Max Act: 4.0625. Min Act: -0.1700

Data Index: 6934828 (Open Web Text)

Max Activating Token Index: 54

Text #4

Max Range: 4.1234. Min Range: -4.1234

Max Act: 4.0373. Min Act: -0.1700

Data Index: 6258658 (Open Web Text)

Max Activating Token Index: 645

Text #5

Max Range: 4.1234. Min Range: -4.1234

Max Act: 4.0343. Min Act: -0.1700

Data Index: 1066025 (Open Web Text)

Max Activating Token Index: 999

Text #6

Max Range: 4.1234. Min Range: -4.1234

Max Act: 4.0078. Min Act: -0.1700

Data Index: 3018535 (Open Web Text)

Max Activating Token Index: 50

Text #7

Max Range: 4.1234. Min Range: -4.1234

Max Act: 4.0194. Min Act: -0.1700

Data Index: 2105618 (Open Web Text)

Max Activating Token Index: 25

Text #8

Max Range: 4.1234. Min Range: -4.1234

Max Act: 4.0363. Min Act: -0.1700

Data Index: 1960242 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 4.1234. Min Range: -4.1234

Max Act: 3.9900. Min Act: -0.1700

Data Index: 1977742 (Open Web Text)

Max Activating Token Index: 743

Text #10

Max Range: 4.1234. Min Range: -4.1234

Max Act: 4.0080. Min Act: -0.1700

Data Index: 2203033 (Open Web Text)

Max Activating Token Index: 946

Text #11

Max Range: 4.1234. Min Range: -4.1234

Max Act: 4.0028. Min Act: -0.1700

Data Index: 1638207 (Open Web Text)

Max Activating Token Index: 415

Text #12

Max Range: 4.1234. Min Range: -4.1234

Max Act: 3.9933. Min Act: -0.1700

Data Index: 4880215 (Open Web Text)

Max Activating Token Index: 533

Text #13

Max Range: 4.1234. Min Range: -4.1234

Max Act: 4.0021. Min Act: -0.1700

Data Index: 6275518 (Open Web Text)

Max Activating Token Index: 964

Text #14

Max Range: 4.1234. Min Range: -4.1234

Max Act: 3.9798. Min Act: -0.1700

Data Index: 1498848 (Open Web Text)

Max Activating Token Index: 450

Text #15

Max Range: 4.1234. Min Range: -4.1234

Max Act: 4.0043. Min Act: -0.1700

Data Index: 8480092 (Open Web Text)

Max Activating Token Index: 931

Text #16

Max Range: 4.1234. Min Range: -4.1234

Max Act: 3.9716. Min Act: -0.1700

Data Index: 1898285 (Open Web Text)

Max Activating Token Index: 966

Text #17

Max Range: 4.1234. Min Range: -4.1234

Max Act: 3.9829. Min Act: -0.1700

Data Index: 3206509 (Open Web Text)

Max Activating Token Index: 426

Text #18

Max Range: 4.1234. Min Range: -4.1234

Max Act: 3.9853. Min Act: -0.1700

Data Index: 3732175 (Open Web Text)

Max Activating Token Index: 564

Text #19

Max Range: 4.1234. Min Range: -4.1234

Max Act: 3.9939. Min Act: -0.1700

Data Index: 4504236 (Open Web Text)

Max Activating Token Index: 116