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

Dataset: Open Web Text

Neuron 481 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: 5.2432. Min Range: -5.2432

Max Act: 5.2432. Min Act: -0.1700

Data Index: 2953628 (Open Web Text)

Max Activating Token Index: 127

Text #1

Max Range: 5.2432. Min Range: -5.2432

Max Act: 5.1460. Min Act: -0.1700

Data Index: 2428388 (Open Web Text)

Max Activating Token Index: 774

Text #2

Max Range: 5.2432. Min Range: -5.2432

Max Act: 5.0140. Min Act: -0.1700

Data Index: 3196014 (Open Web Text)

Max Activating Token Index: 85

Text #3

Max Range: 5.2432. Min Range: -5.2432

Max Act: 4.9749. Min Act: -0.1700

Data Index: 7093320 (Open Web Text)

Max Activating Token Index: 866

Text #4

Max Range: 5.2432. Min Range: -5.2432

Max Act: 4.9382. Min Act: -0.1700

Data Index: 206576 (Open Web Text)

Max Activating Token Index: 812

Text #5

Max Range: 5.2432. Min Range: -5.2432

Max Act: 4.8844. Min Act: -0.1700

Data Index: 7106172 (Open Web Text)

Max Activating Token Index: 718

Text #6

Max Range: 5.2432. Min Range: -5.2432

Max Act: 4.8834. Min Act: -0.1700

Data Index: 4642445 (Open Web Text)

Max Activating Token Index: 425

Text #7

Max Range: 5.2432. Min Range: -5.2432

Max Act: 4.9320. Min Act: -0.1700

Data Index: 3166899 (Open Web Text)

Max Activating Token Index: 695

Text #8

Max Range: 5.2432. Min Range: -5.2432

Max Act: 4.9428. Min Act: -0.1700

Data Index: 1415548 (Open Web Text)

Max Activating Token Index: 694

Text #9

Max Range: 5.2432. Min Range: -5.2432

Max Act: 4.8663. Min Act: -0.1700

Data Index: 5173683 (Open Web Text)

Max Activating Token Index: 1013

Text #10

Max Range: 5.2432. Min Range: -5.2432

Max Act: 4.8847. Min Act: -0.1700

Data Index: 1106306 (Open Web Text)

Max Activating Token Index: 816

Text #11

Max Range: 5.2432. Min Range: -5.2432

Max Act: 4.8497. Min Act: -0.1700

Data Index: 2337081 (Open Web Text)

Max Activating Token Index: 619

Text #12

Max Range: 5.2432. Min Range: -5.2432

Max Act: 4.7945. Min Act: -0.1700

Data Index: 90833 (Open Web Text)

Max Activating Token Index: 110

Text #13

Max Range: 5.2432. Min Range: -5.2432

Max Act: 4.8299. Min Act: -0.1700

Data Index: 5239421 (Open Web Text)

Max Activating Token Index: 465

Text #14

Max Range: 5.2432. Min Range: -5.2432

Max Act: 4.7904. Min Act: -0.1700

Data Index: 1102941 (Open Web Text)

Max Activating Token Index: 865

Text #15

Max Range: 5.2432. Min Range: -5.2432

Max Act: 4.7071. Min Act: -0.1700

Data Index: 2574997 (Open Web Text)

Max Activating Token Index: 999

Text #16

Max Range: 5.2432. Min Range: -5.2432

Max Act: 4.7805. Min Act: -0.1700

Data Index: 2042542 (Open Web Text)

Max Activating Token Index: 350

Text #17

Max Range: 5.2432. Min Range: -5.2432

Max Act: 4.7760. Min Act: -0.1700

Data Index: 5323965 (Open Web Text)

Max Activating Token Index: 826

Text #18

Max Range: 5.2432. Min Range: -5.2432

Max Act: 4.7706. Min Act: -0.1700

Data Index: 1372268 (Open Web Text)

Max Activating Token Index: 423

Text #19

Max Range: 5.2432. Min Range: -5.2432

Max Act: 4.6858. Min Act: -0.1700

Data Index: 862737 (Open Web Text)

Max Activating Token Index: 996