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

Dataset: Open Web Text

Neuron 3033 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: 3.2222. Min Range: -3.2222

Max Act: 3.2222. Min Act: -0.1700

Data Index: 3634128 (Open Web Text)

Max Activating Token Index: 377

Text #1

Max Range: 3.2222. Min Range: -3.2222

Max Act: 3.2183. Min Act: -0.1700

Data Index: 3213731 (Open Web Text)

Max Activating Token Index: 1022

Text #2

Max Range: 3.2222. Min Range: -3.2222

Max Act: 3.1991. Min Act: -0.1700

Data Index: 8399259 (Open Web Text)

Max Activating Token Index: 678

Text #3

Max Range: 3.2222. Min Range: -3.2222

Max Act: 3.1950. Min Act: -0.1700

Data Index: 1522967 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.2222. Min Range: -3.2222

Max Act: 3.1830. Min Act: -0.1700

Data Index: 6275861 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.2222. Min Range: -3.2222

Max Act: 3.1941. Min Act: -0.1700

Data Index: 773159 (Open Web Text)

Max Activating Token Index: 917

Text #6

Max Range: 3.2222. Min Range: -3.2222

Max Act: 3.1905. Min Act: -0.1700

Data Index: 8069552 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.2222. Min Range: -3.2222

Max Act: 3.1806. Min Act: -0.1700

Data Index: 4679091 (Open Web Text)

Max Activating Token Index: 1002

Text #8

Max Range: 3.2222. Min Range: -3.2222

Max Act: 3.1527. Min Act: -0.1700

Data Index: 4384708 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.2222. Min Range: -3.2222

Max Act: 3.1509. Min Act: -0.1700

Data Index: 694592 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 3.2222. Min Range: -3.2222

Max Act: 3.1629. Min Act: -0.1700

Data Index: 8258402 (Open Web Text)

Max Activating Token Index: 302

Text #11

Max Range: 3.2222. Min Range: -3.2222

Max Act: 3.1600. Min Act: -0.1700

Data Index: 6499789 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.2222. Min Range: -3.2222

Max Act: 3.1430. Min Act: -0.1700

Data Index: 3534822 (Open Web Text)

Max Activating Token Index: 327

Text #13

Max Range: 3.2222. Min Range: -3.2222

Max Act: 3.1573. Min Act: -0.1700

Data Index: 7027732 (Open Web Text)

Max Activating Token Index: 981

Text #14

Max Range: 3.2222. Min Range: -3.2222

Max Act: 3.1299. Min Act: -0.1700

Data Index: 2480809 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 3.2222. Min Range: -3.2222

Max Act: 3.1342. Min Act: -0.1700

Data Index: 5201490 (Open Web Text)

Max Activating Token Index: 375

Text #16

Max Range: 3.2222. Min Range: -3.2222

Max Act: 3.1394. Min Act: -0.1700

Data Index: 3872844 (Open Web Text)

Max Activating Token Index: 39

Text #17

Max Range: 3.2222. Min Range: -3.2222

Max Act: 3.1142. Min Act: -0.1700

Data Index: 727814 (Open Web Text)

Max Activating Token Index: 476

Text #18

Max Range: 3.2222. Min Range: -3.2222

Max Act: 3.1149. Min Act: -0.1700

Data Index: 7672327 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 3.2222. Min Range: -3.2222

Max Act: 3.1248. Min Act: -0.1700

Data Index: 6236618 (Open Web Text)

Max Activating Token Index: 544