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

Dataset: Open Web Text

Neuron 2310 in Layer 5

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: 3.3506. Min Range: -3.3506

Max Act: 3.3308. Min Act: -0.1700

Data Index: 1069663 (Open Web Text)

Max Activating Token Index: 838

Text #1

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.3506. Min Act: -0.1700

Data Index: 8222642 (Open Web Text)

Max Activating Token Index: 271

Text #2

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.3024. Min Act: -0.1700

Data Index: 6148980 (Open Web Text)

Max Activating Token Index: 542

Text #3

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.3141. Min Act: -0.1700

Data Index: 3224279 (Open Web Text)

Max Activating Token Index: 924

Text #4

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.2590. Min Act: -0.1700

Data Index: 3783113 (Open Web Text)

Max Activating Token Index: 201

Text #5

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.2234. Min Act: -0.1700

Data Index: 2415252 (Open Web Text)

Max Activating Token Index: 543

Text #6

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.1656. Min Act: -0.1700

Data Index: 8207808 (Open Web Text)

Max Activating Token Index: 554

Text #7

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.1321. Min Act: -0.1700

Data Index: 4309923 (Open Web Text)

Max Activating Token Index: 986

Text #8

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.1153. Min Act: -0.1700

Data Index: 6506081 (Open Web Text)

Max Activating Token Index: 598

Text #9

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.1183. Min Act: -0.1700

Data Index: 7548407 (Open Web Text)

Max Activating Token Index: 613

Text #10

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.1133. Min Act: -0.1700

Data Index: 1398383 (Open Web Text)

Max Activating Token Index: 994

Text #11

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.1173. Min Act: -0.1700

Data Index: 1760021 (Open Web Text)

Max Activating Token Index: 723

Text #12

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.0953. Min Act: -0.1700

Data Index: 2942179 (Open Web Text)

Max Activating Token Index: 425

Text #13

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.0949. Min Act: -0.1700

Data Index: 3151312 (Open Web Text)

Max Activating Token Index: 1005

Text #14

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.0783. Min Act: -0.1700

Data Index: 609049 (Open Web Text)

Max Activating Token Index: 697

Text #15

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.0771. Min Act: -0.1700

Data Index: 6288393 (Open Web Text)

Max Activating Token Index: 567

Text #16

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.0693. Min Act: -0.1700

Data Index: 4623408 (Open Web Text)

Max Activating Token Index: 965

Text #17

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.0810. Min Act: -0.1700

Data Index: 773869 (Open Web Text)

Max Activating Token Index: 398

Text #18

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.0335. Min Act: -0.1700

Data Index: 7661807 (Open Web Text)

Max Activating Token Index: 34

Text #19

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.0394. Min Act: -0.1700

Data Index: 6792272 (Open Web Text)

Max Activating Token Index: 244