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

Dataset: Open Web Text

Neuron 1805 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: 2.3559. Min Range: -2.3559

Max Act: 2.3559. Min Act: -0.1700

Data Index: 3537502 (Open Web Text)

Max Activating Token Index: 327

Text #1

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2623. Min Act: -0.1700

Data Index: 5679757 (Open Web Text)

Max Activating Token Index: 516

Text #2

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2809. Min Act: -0.1700

Data Index: 2443844 (Open Web Text)

Max Activating Token Index: 415

Text #3

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2578. Min Act: -0.1700

Data Index: 981259 (Open Web Text)

Max Activating Token Index: 431

Text #4

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2488. Min Act: -0.1700

Data Index: 1822718 (Open Web Text)

Max Activating Token Index: 234

Text #5

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2333. Min Act: -0.1700

Data Index: 4170172 (Open Web Text)

Max Activating Token Index: 583

Text #6

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2260. Min Act: -0.1700

Data Index: 2940841 (Open Web Text)

Max Activating Token Index: 481

Text #7

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2061. Min Act: -0.1700

Data Index: 1412510 (Open Web Text)

Max Activating Token Index: 219

Text #8

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2026. Min Act: -0.1700

Data Index: 3515327 (Open Web Text)

Max Activating Token Index: 385

Text #9

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2018. Min Act: -0.1700

Data Index: 1491313 (Open Web Text)

Max Activating Token Index: 442

Text #10

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.1846. Min Act: -0.1700

Data Index: 296352 (Open Web Text)

Max Activating Token Index: 371

Text #11

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2054. Min Act: -0.1700

Data Index: 2008230 (Open Web Text)

Max Activating Token Index: 642

Text #12

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2000. Min Act: -0.1700

Data Index: 6803481 (Open Web Text)

Max Activating Token Index: 866

Text #13

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.1869. Min Act: -0.1700

Data Index: 6899330 (Open Web Text)

Max Activating Token Index: 472

Text #14

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.1911. Min Act: -0.1700

Data Index: 5586217 (Open Web Text)

Max Activating Token Index: 131

Text #15

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.1737. Min Act: -0.1700

Data Index: 6119454 (Open Web Text)

Max Activating Token Index: 365

Text #16

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.1757. Min Act: -0.1700

Data Index: 3555373 (Open Web Text)

Max Activating Token Index: 109

Text #17

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2048. Min Act: -0.1700

Data Index: 6682983 (Open Web Text)

Max Activating Token Index: 1006

Text #18

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.1733. Min Act: -0.1700

Data Index: 3509836 (Open Web Text)

Max Activating Token Index: 915

Text #19

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.1762. Min Act: -0.1700

Data Index: 5974462 (Open Web Text)

Max Activating Token Index: 250