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

Dataset: Open Web Text

Neuron 1609 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: 4.4056. Min Range: -4.4056

Max Act: 4.4056. Min Act: -0.1700

Data Index: 5382231 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.4056. Min Range: -4.4056

Max Act: 4.1769. Min Act: -0.1700

Data Index: 5600081 (Open Web Text)

Max Activating Token Index: 958

Text #2

Max Range: 4.4056. Min Range: -4.4056

Max Act: 4.1647. Min Act: -0.1700

Data Index: 2195860 (Open Web Text)

Max Activating Token Index: 446

Text #3

Max Range: 4.4056. Min Range: -4.4056

Max Act: 4.0691. Min Act: -0.1700

Data Index: 1374488 (Open Web Text)

Max Activating Token Index: 640

Text #4

Max Range: 4.4056. Min Range: -4.4056

Max Act: 4.0598. Min Act: -0.1700

Data Index: 3085288 (Open Web Text)

Max Activating Token Index: 415

Text #5

Max Range: 4.4056. Min Range: -4.4056

Max Act: 4.0394. Min Act: -0.1700

Data Index: 8080554 (Open Web Text)

Max Activating Token Index: 641

Text #6

Max Range: 4.4056. Min Range: -4.4056

Max Act: 4.0576. Min Act: -0.1700

Data Index: 8601099 (Open Web Text)

Max Activating Token Index: 598

Text #7

Max Range: 4.4056. Min Range: -4.4056

Max Act: 3.9959. Min Act: -0.1700

Data Index: 1392247 (Open Web Text)

Max Activating Token Index: 619

Text #8

Max Range: 4.4056. Min Range: -4.4056

Max Act: 3.9519. Min Act: -0.1700

Data Index: 7068690 (Open Web Text)

Max Activating Token Index: 886

Text #9

Max Range: 4.4056. Min Range: -4.4056

Max Act: 3.9863. Min Act: -0.1700

Data Index: 6376088 (Open Web Text)

Max Activating Token Index: 524

Text #10

Max Range: 4.4056. Min Range: -4.4056

Max Act: 3.9457. Min Act: -0.1700

Data Index: 8805303 (Open Web Text)

Max Activating Token Index: 625

Text #11

Max Range: 4.4056. Min Range: -4.4056

Max Act: 3.9259. Min Act: -0.1700

Data Index: 1401616 (Open Web Text)

Max Activating Token Index: 347

Text #12

Max Range: 4.4056. Min Range: -4.4056

Max Act: 3.9301. Min Act: -0.1700

Data Index: 6879787 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.4056. Min Range: -4.4056

Max Act: 3.9374. Min Act: -0.1700

Data Index: 7943167 (Open Web Text)

Max Activating Token Index: 369

Text #14

Max Range: 4.4056. Min Range: -4.4056

Max Act: 3.9200. Min Act: -0.1700

Data Index: 6359858 (Open Web Text)

Max Activating Token Index: 173

Text #15

Max Range: 4.4056. Min Range: -4.4056

Max Act: 3.9136. Min Act: -0.1700

Data Index: 510663 (Open Web Text)

Max Activating Token Index: 963

Text #16

Max Range: 4.4056. Min Range: -4.4056

Max Act: 3.9383. Min Act: -0.1700

Data Index: 6412081 (Open Web Text)

Max Activating Token Index: 756

Text #17

Max Range: 4.4056. Min Range: -4.4056

Max Act: 3.9142. Min Act: -0.1700

Data Index: 2190785 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.4056. Min Range: -4.4056

Max Act: 3.9192. Min Act: -0.1700

Data Index: 7332279 (Open Web Text)

Max Activating Token Index: 851

Text #19

Max Range: 4.4056. Min Range: -4.4056

Max Act: 3.9032. Min Act: -0.1700

Data Index: 3863071 (Open Web Text)

Max Activating Token Index: 345