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

Dataset: Open Web Text

Neuron 598 in Layer 4

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: 4.2373. Min Range: -4.2373

Max Act: 4.1796. Min Act: -0.1700

Data Index: 7533858 (Open Web Text)

Max Activating Token Index: 697

Text #1

Max Range: 4.2373. Min Range: -4.2373

Max Act: 4.2179. Min Act: -0.1700

Data Index: 6070029 (Open Web Text)

Max Activating Token Index: 689

Text #2

Max Range: 4.2373. Min Range: -4.2373

Max Act: 4.2373. Min Act: -0.1700

Data Index: 6621629 (Open Web Text)

Max Activating Token Index: 861

Text #3

Max Range: 4.2373. Min Range: -4.2373

Max Act: 4.1595. Min Act: -0.1700

Data Index: 5576501 (Open Web Text)

Max Activating Token Index: 894

Text #4

Max Range: 4.2373. Min Range: -4.2373

Max Act: 4.1773. Min Act: -0.1700

Data Index: 5601448 (Open Web Text)

Max Activating Token Index: 426

Text #5

Max Range: 4.2373. Min Range: -4.2373

Max Act: 4.1676. Min Act: -0.1700

Data Index: 4908061 (Open Web Text)

Max Activating Token Index: 624

Text #6

Max Range: 4.2373. Min Range: -4.2373

Max Act: 4.0854. Min Act: -0.1700

Data Index: 5532723 (Open Web Text)

Max Activating Token Index: 920

Text #7

Max Range: 4.2373. Min Range: -4.2373

Max Act: 4.0491. Min Act: -0.1700

Data Index: 4915840 (Open Web Text)

Max Activating Token Index: 337

Text #8

Max Range: 4.2373. Min Range: -4.2373

Max Act: 4.1141. Min Act: -0.1700

Data Index: 8154453 (Open Web Text)

Max Activating Token Index: 949

Text #9

Max Range: 4.2373. Min Range: -4.2373

Max Act: 4.0750. Min Act: -0.1700

Data Index: 8543466 (Open Web Text)

Max Activating Token Index: 742

Text #10

Max Range: 4.2373. Min Range: -4.2373

Max Act: 4.0315. Min Act: -0.1700

Data Index: 8691684 (Open Web Text)

Max Activating Token Index: 993

Text #11

Max Range: 4.2373. Min Range: -4.2373

Max Act: 4.0538. Min Act: -0.1700

Data Index: 2737785 (Open Web Text)

Max Activating Token Index: 994

Text #12

Max Range: 4.2373. Min Range: -4.2373

Max Act: 3.9745. Min Act: -0.1700

Data Index: 1501038 (Open Web Text)

Max Activating Token Index: 497

Text #13

Max Range: 4.2373. Min Range: -4.2373

Max Act: 4.0519. Min Act: -0.1700

Data Index: 1795014 (Open Web Text)

Max Activating Token Index: 317

Text #14

Max Range: 4.2373. Min Range: -4.2373

Max Act: 4.0609. Min Act: -0.1700

Data Index: 7531482 (Open Web Text)

Max Activating Token Index: 984

Text #15

Max Range: 4.2373. Min Range: -4.2373

Max Act: 4.1106. Min Act: -0.1700

Data Index: 4404509 (Open Web Text)

Max Activating Token Index: 162

Text #16

Max Range: 4.2373. Min Range: -4.2373

Max Act: 4.0105. Min Act: -0.1700

Data Index: 7094787 (Open Web Text)

Max Activating Token Index: 642

Text #17

Max Range: 4.2373. Min Range: -4.2373

Max Act: 3.9842. Min Act: -0.1700

Data Index: 6460052 (Open Web Text)

Max Activating Token Index: 821

Text #18

Max Range: 4.2373. Min Range: -4.2373

Max Act: 4.0389. Min Act: -0.1700

Data Index: 2851777 (Open Web Text)

Max Activating Token Index: 1004

Text #19

Max Range: 4.2373. Min Range: -4.2373

Max Act: 3.9947. Min Act: -0.1700

Data Index: 4920914 (Open Web Text)

Max Activating Token Index: 897