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

Dataset: Open Web Text

Neuron 1286 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: 3.2656. Min Range: -3.2656

Max Act: 3.2656. Min Act: -0.1700

Data Index: 3284708 (Open Web Text)

Max Activating Token Index: 508

Text #1

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.1628. Min Act: -0.1700

Data Index: 4997328 (Open Web Text)

Max Activating Token Index: 733

Text #2

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.1725. Min Act: -0.1700

Data Index: 2891667 (Open Web Text)

Max Activating Token Index: 473

Text #3

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.1558. Min Act: -0.1700

Data Index: 1070970 (Open Web Text)

Max Activating Token Index: 479

Text #4

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.1500. Min Act: -0.1700

Data Index: 6964864 (Open Web Text)

Max Activating Token Index: 166

Text #5

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.1405. Min Act: -0.1700

Data Index: 433598 (Open Web Text)

Max Activating Token Index: 475

Text #6

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.1615. Min Act: -0.1700

Data Index: 182 (Open Web Text)

Max Activating Token Index: 888

Text #7

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.1580. Min Act: -0.1700

Data Index: 3143085 (Open Web Text)

Max Activating Token Index: 946

Text #8

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.1077. Min Act: -0.1700

Data Index: 7674824 (Open Web Text)

Max Activating Token Index: 956

Text #9

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.0834. Min Act: -0.1700

Data Index: 2537669 (Open Web Text)

Max Activating Token Index: 745

Text #10

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.1264. Min Act: -0.1700

Data Index: 6836607 (Open Web Text)

Max Activating Token Index: 437

Text #11

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.0819. Min Act: -0.1700

Data Index: 2133075 (Open Web Text)

Max Activating Token Index: 755

Text #12

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.0716. Min Act: -0.1700

Data Index: 7609533 (Open Web Text)

Max Activating Token Index: 279

Text #13

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.0759. Min Act: -0.1700

Data Index: 6193900 (Open Web Text)

Max Activating Token Index: 54

Text #14

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.0415. Min Act: -0.1700

Data Index: 8750645 (Open Web Text)

Max Activating Token Index: 1006

Text #15

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.0562. Min Act: -0.1700

Data Index: 5824829 (Open Web Text)

Max Activating Token Index: 114

Text #16

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.0329. Min Act: -0.1700

Data Index: 1205010 (Open Web Text)

Max Activating Token Index: 142

Text #17

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.0254. Min Act: -0.1700

Data Index: 1073759 (Open Web Text)

Max Activating Token Index: 645

Text #18

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.0237. Min Act: -0.1700

Data Index: 53452 (Open Web Text)

Max Activating Token Index: 312

Text #19

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.0155. Min Act: -0.1700

Data Index: 580316 (Open Web Text)

Max Activating Token Index: 575