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

Dataset: Open Web Text

Neuron 1908 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: 3.7104. Min Range: -3.7104

Max Act: 3.7104. Min Act: -0.1700

Data Index: 155575 (Open Web Text)

Max Activating Token Index: 716

Text #1

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6832. Min Act: -0.1700

Data Index: 5708418 (Open Web Text)

Max Activating Token Index: 502

Text #2

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6733. Min Act: -0.1700

Data Index: 2792453 (Open Web Text)

Max Activating Token Index: 721

Text #3

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6725. Min Act: -0.1700

Data Index: 4751245 (Open Web Text)

Max Activating Token Index: 751

Text #4

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6670. Min Act: -0.1700

Data Index: 3437353 (Open Web Text)

Max Activating Token Index: 666

Text #5

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6534. Min Act: -0.1700

Data Index: 3978110 (Open Web Text)

Max Activating Token Index: 615

Text #6

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6607. Min Act: -0.1700

Data Index: 1180156 (Open Web Text)

Max Activating Token Index: 433

Text #7

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6403. Min Act: -0.1700

Data Index: 4411190 (Open Web Text)

Max Activating Token Index: 766

Text #8

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6634. Min Act: -0.1700

Data Index: 4316927 (Open Web Text)

Max Activating Token Index: 633

Text #9

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6073. Min Act: -0.1700

Data Index: 4689453 (Open Web Text)

Max Activating Token Index: 551

Text #10

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6291. Min Act: -0.1700

Data Index: 860711 (Open Web Text)

Max Activating Token Index: 662

Text #11

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6321. Min Act: -0.1700

Data Index: 590564 (Open Web Text)

Max Activating Token Index: 753

Text #12

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6347. Min Act: -0.1700

Data Index: 3336228 (Open Web Text)

Max Activating Token Index: 701

Text #13

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.5998. Min Act: -0.1700

Data Index: 3053139 (Open Web Text)

Max Activating Token Index: 754

Text #14

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6166. Min Act: -0.1700

Data Index: 4810319 (Open Web Text)

Max Activating Token Index: 221

Text #15

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6324. Min Act: -0.1700

Data Index: 5243028 (Open Web Text)

Max Activating Token Index: 713

Text #16

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6168. Min Act: -0.1700

Data Index: 5907149 (Open Web Text)

Max Activating Token Index: 506

Text #17

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6107. Min Act: -0.1700

Data Index: 7327063 (Open Web Text)

Max Activating Token Index: 381

Text #18

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6231. Min Act: -0.1700

Data Index: 289829 (Open Web Text)

Max Activating Token Index: 1005

Text #19

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.5973. Min Act: -0.1700

Data Index: 7751358 (Open Web Text)

Max Activating Token Index: 360