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

Dataset: Open Web Text

Neuron 2626 in Layer 3

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: 3.0598. Min Range: -3.0598

Max Act: 3.0598. Min Act: -0.1700

Data Index: 925431 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.0598. Min Range: -3.0598

Max Act: 3.0467. Min Act: -0.1700

Data Index: 913631 (Open Web Text)

Max Activating Token Index: 462

Text #2

Max Range: 3.0598. Min Range: -3.0598

Max Act: 2.9989. Min Act: -0.1700

Data Index: 1483159 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.0598. Min Range: -3.0598

Max Act: 3.0289. Min Act: -0.1700

Data Index: 1985529 (Open Web Text)

Max Activating Token Index: 357

Text #4

Max Range: 3.0598. Min Range: -3.0598

Max Act: 2.9934. Min Act: -0.1700

Data Index: 3285522 (Open Web Text)

Max Activating Token Index: 188

Text #5

Max Range: 3.0598. Min Range: -3.0598

Max Act: 2.9712. Min Act: -0.1700

Data Index: 2236172 (Open Web Text)

Max Activating Token Index: 701

Text #6

Max Range: 3.0598. Min Range: -3.0598

Max Act: 2.9951. Min Act: -0.1700

Data Index: 8023130 (Open Web Text)

Max Activating Token Index: 186

Text #7

Max Range: 3.0598. Min Range: -3.0598

Max Act: 2.9846. Min Act: -0.1700

Data Index: 8263299 (Open Web Text)

Max Activating Token Index: 48

Text #8

Max Range: 3.0598. Min Range: -3.0598

Max Act: 2.9655. Min Act: -0.1700

Data Index: 6533396 (Open Web Text)

Max Activating Token Index: 523

Text #9

Max Range: 3.0598. Min Range: -3.0598

Max Act: 3.0344. Min Act: -0.1700

Data Index: 6807011 (Open Web Text)

Max Activating Token Index: 291

Text #10

Max Range: 3.0598. Min Range: -3.0598

Max Act: 2.9449. Min Act: -0.1700

Data Index: 2434388 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.0598. Min Range: -3.0598

Max Act: 2.9449. Min Act: -0.1700

Data Index: 3809253 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.0598. Min Range: -3.0598

Max Act: 2.9474. Min Act: -0.1700

Data Index: 3583325 (Open Web Text)

Max Activating Token Index: 582

Text #13

Max Range: 3.0598. Min Range: -3.0598

Max Act: 2.8873. Min Act: -0.1700

Data Index: 3370526 (Open Web Text)

Max Activating Token Index: 409

Text #14

Max Range: 3.0598. Min Range: -3.0598

Max Act: 2.9025. Min Act: -0.1700

Data Index: 2619029 (Open Web Text)

Max Activating Token Index: 450

Text #15

Max Range: 3.0598. Min Range: -3.0598

Max Act: 2.8592. Min Act: -0.1700

Data Index: 4225603 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.0598. Min Range: -3.0598

Max Act: 2.9370. Min Act: -0.1700

Data Index: 7083155 (Open Web Text)

Max Activating Token Index: 796

Text #17

Max Range: 3.0598. Min Range: -3.0598

Max Act: 2.9240. Min Act: -0.1700

Data Index: 1672791 (Open Web Text)

Max Activating Token Index: 555

Text #18

Max Range: 3.0598. Min Range: -3.0598

Max Act: 2.9288. Min Act: -0.1700

Data Index: 6291669 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.0598. Min Range: -3.0598

Max Act: 2.9269. Min Act: -0.1700

Data Index: 4197856 (Open Web Text)

Max Activating Token Index: 232