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

Dataset: Open Web Text

Neuron 1920 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: 3.7089. Min Range: -3.7089

Max Act: 3.7089. Min Act: -0.1700

Data Index: 1392978 (Open Web Text)

Max Activating Token Index: 161

Text #1

Max Range: 3.7089. Min Range: -3.7089

Max Act: 3.7040. Min Act: -0.1700

Data Index: 1353906 (Open Web Text)

Max Activating Token Index: 369

Text #2

Max Range: 3.7089. Min Range: -3.7089

Max Act: 3.6597. Min Act: -0.1700

Data Index: 7871556 (Open Web Text)

Max Activating Token Index: 384

Text #3

Max Range: 3.7089. Min Range: -3.7089

Max Act: 3.6695. Min Act: -0.1700

Data Index: 3477109 (Open Web Text)

Max Activating Token Index: 1003

Text #4

Max Range: 3.7089. Min Range: -3.7089

Max Act: 3.6479. Min Act: -0.1700

Data Index: 2532507 (Open Web Text)

Max Activating Token Index: 255

Text #5

Max Range: 3.7089. Min Range: -3.7089

Max Act: 3.6401. Min Act: -0.1700

Data Index: 3962543 (Open Web Text)

Max Activating Token Index: 977

Text #6

Max Range: 3.7089. Min Range: -3.7089

Max Act: 3.6650. Min Act: -0.1700

Data Index: 4518441 (Open Web Text)

Max Activating Token Index: 214

Text #7

Max Range: 3.7089. Min Range: -3.7089

Max Act: 3.6126. Min Act: -0.1700

Data Index: 2271935 (Open Web Text)

Max Activating Token Index: 306

Text #8

Max Range: 3.7089. Min Range: -3.7089

Max Act: 3.6248. Min Act: -0.1700

Data Index: 2243036 (Open Web Text)

Max Activating Token Index: 287

Text #9

Max Range: 3.7089. Min Range: -3.7089

Max Act: 3.6304. Min Act: -0.1700

Data Index: 5681973 (Open Web Text)

Max Activating Token Index: 347

Text #10

Max Range: 3.7089. Min Range: -3.7089

Max Act: 3.6247. Min Act: -0.1700

Data Index: 3126512 (Open Web Text)

Max Activating Token Index: 366

Text #11

Max Range: 3.7089. Min Range: -3.7089

Max Act: 3.6085. Min Act: -0.1700

Data Index: 4009454 (Open Web Text)

Max Activating Token Index: 630

Text #12

Max Range: 3.7089. Min Range: -3.7089

Max Act: 3.6068. Min Act: -0.1700

Data Index: 5942184 (Open Web Text)

Max Activating Token Index: 764

Text #13

Max Range: 3.7089. Min Range: -3.7089

Max Act: 3.5853. Min Act: -0.1700

Data Index: 6144532 (Open Web Text)

Max Activating Token Index: 857

Text #14

Max Range: 3.7089. Min Range: -3.7089

Max Act: 3.5933. Min Act: -0.1700

Data Index: 6365135 (Open Web Text)

Max Activating Token Index: 652

Text #15

Max Range: 3.7089. Min Range: -3.7089

Max Act: 3.5861. Min Act: -0.1700

Data Index: 6649868 (Open Web Text)

Max Activating Token Index: 455

Text #16

Max Range: 3.7089. Min Range: -3.7089

Max Act: 3.5877. Min Act: -0.1700

Data Index: 6976545 (Open Web Text)

Max Activating Token Index: 428

Text #17

Max Range: 3.7089. Min Range: -3.7089

Max Act: 3.5855. Min Act: -0.1700

Data Index: 6990011 (Open Web Text)

Max Activating Token Index: 777

Text #18

Max Range: 3.7089. Min Range: -3.7089

Max Act: 3.6108. Min Act: -0.1700

Data Index: 2376178 (Open Web Text)

Max Activating Token Index: 586

Text #19

Max Range: 3.7089. Min Range: -3.7089

Max Act: 3.5816. Min Act: -0.1700

Data Index: 2737922 (Open Web Text)

Max Activating Token Index: 554