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

Dataset: Open Web Text

Neuron 633 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: 3.5900. Min Range: -3.5900

Max Act: 3.5900. Min Act: -0.1700

Data Index: 5614399 (Open Web Text)

Max Activating Token Index: 486

Text #1

Max Range: 3.5900. Min Range: -3.5900

Max Act: 3.5850. Min Act: -0.1700

Data Index: 5331426 (Open Web Text)

Max Activating Token Index: 95

Text #2

Max Range: 3.5900. Min Range: -3.5900

Max Act: 3.3969. Min Act: -0.1700

Data Index: 356686 (Open Web Text)

Max Activating Token Index: 933

Text #3

Max Range: 3.5900. Min Range: -3.5900

Max Act: 3.3756. Min Act: -0.1700

Data Index: 2009647 (Open Web Text)

Max Activating Token Index: 588

Text #4

Max Range: 3.5900. Min Range: -3.5900

Max Act: 3.2651. Min Act: -0.1700

Data Index: 8547926 (Open Web Text)

Max Activating Token Index: 33

Text #5

Max Range: 3.5900. Min Range: -3.5900

Max Act: 3.2156. Min Act: -0.1700

Data Index: 7888436 (Open Web Text)

Max Activating Token Index: 685

Text #6

Max Range: 3.5900. Min Range: -3.5900

Max Act: 3.1948. Min Act: -0.1700

Data Index: 6447379 (Open Web Text)

Max Activating Token Index: 783

Text #7

Max Range: 3.5900. Min Range: -3.5900

Max Act: 3.1922. Min Act: -0.1700

Data Index: 2786196 (Open Web Text)

Max Activating Token Index: 961

Text #8

Max Range: 3.5900. Min Range: -3.5900

Max Act: 3.1951. Min Act: -0.1700

Data Index: 6835988 (Open Web Text)

Max Activating Token Index: 801

Text #9

Max Range: 3.5900. Min Range: -3.5900

Max Act: 3.1910. Min Act: -0.1700

Data Index: 1249751 (Open Web Text)

Max Activating Token Index: 808

Text #10

Max Range: 3.5900. Min Range: -3.5900

Max Act: 3.1903. Min Act: -0.1700

Data Index: 1195177 (Open Web Text)

Max Activating Token Index: 691

Text #11

Max Range: 3.5900. Min Range: -3.5900

Max Act: 3.1966. Min Act: -0.1700

Data Index: 3008998 (Open Web Text)

Max Activating Token Index: 255

Text #12

Max Range: 3.5900. Min Range: -3.5900

Max Act: 3.1851. Min Act: -0.1700

Data Index: 1052451 (Open Web Text)

Max Activating Token Index: 879

Text #13

Max Range: 3.5900. Min Range: -3.5900

Max Act: 3.1891. Min Act: -0.1700

Data Index: 815931 (Open Web Text)

Max Activating Token Index: 50

Text #14

Max Range: 3.5900. Min Range: -3.5900

Max Act: 3.1992. Min Act: -0.1700

Data Index: 7484651 (Open Web Text)

Max Activating Token Index: 183

Text #15

Max Range: 3.5900. Min Range: -3.5900

Max Act: 3.1965. Min Act: -0.1700

Data Index: 1793399 (Open Web Text)

Max Activating Token Index: 450

Text #16

Max Range: 3.5900. Min Range: -3.5900

Max Act: 3.1523. Min Act: -0.1700

Data Index: 472801 (Open Web Text)

Max Activating Token Index: 759

Text #17

Max Range: 3.5900. Min Range: -3.5900

Max Act: 3.1423. Min Act: -0.1700

Data Index: 7969233 (Open Web Text)

Max Activating Token Index: 380

Text #18

Max Range: 3.5900. Min Range: -3.5900

Max Act: 3.1920. Min Act: -0.1700

Data Index: 8441388 (Open Web Text)

Max Activating Token Index: 998

Text #19

Max Range: 3.5900. Min Range: -3.5900

Max Act: 3.1679. Min Act: -0.1700

Data Index: 1063310 (Open Web Text)

Max Activating Token Index: 305