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

Dataset: Open Web Text

Neuron 1960 in Layer 6

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: 3.4506. Min Range: -3.4506

Max Act: 3.4506. Min Act: -0.1700

Data Index: 5814228 (Open Web Text)

Max Activating Token Index: 776

Text #1

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.3700. Min Act: -0.1700

Data Index: 4271689 (Open Web Text)

Max Activating Token Index: 350

Text #2

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.3066. Min Act: -0.1700

Data Index: 7245331 (Open Web Text)

Max Activating Token Index: 653

Text #3

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2987. Min Act: -0.1700

Data Index: 6974756 (Open Web Text)

Max Activating Token Index: 824

Text #4

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2978. Min Act: -0.1700

Data Index: 6384762 (Open Web Text)

Max Activating Token Index: 825

Text #5

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2628. Min Act: -0.1700

Data Index: 3447532 (Open Web Text)

Max Activating Token Index: 750

Text #6

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2523. Min Act: -0.1700

Data Index: 5058311 (Open Web Text)

Max Activating Token Index: 461

Text #7

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2535. Min Act: -0.1700

Data Index: 4295215 (Open Web Text)

Max Activating Token Index: 701

Text #8

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2407. Min Act: -0.1700

Data Index: 8312005 (Open Web Text)

Max Activating Token Index: 194

Text #9

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2300. Min Act: -0.1700

Data Index: 7420644 (Open Web Text)

Max Activating Token Index: 539

Text #10

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2268. Min Act: -0.1700

Data Index: 1240539 (Open Web Text)

Max Activating Token Index: 105

Text #11

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2450. Min Act: -0.1700

Data Index: 3012368 (Open Web Text)

Max Activating Token Index: 294

Text #12

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2652. Min Act: -0.1700

Data Index: 6771664 (Open Web Text)

Max Activating Token Index: 199

Text #13

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2387. Min Act: -0.1700

Data Index: 4095173 (Open Web Text)

Max Activating Token Index: 953

Text #14

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2433. Min Act: -0.1700

Data Index: 8093904 (Open Web Text)

Max Activating Token Index: 980

Text #15

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2388. Min Act: -0.1700

Data Index: 5401303 (Open Web Text)

Max Activating Token Index: 427

Text #16

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2236. Min Act: -0.1700

Data Index: 8823384 (Open Web Text)

Max Activating Token Index: 845

Text #17

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2264. Min Act: -0.1700

Data Index: 1494591 (Open Web Text)

Max Activating Token Index: 480

Text #18

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2121. Min Act: -0.1700

Data Index: 7747916 (Open Web Text)

Max Activating Token Index: 651

Text #19

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.1890. Min Act: -0.1700

Data Index: 8449486 (Open Web Text)

Max Activating Token Index: 487