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

Dataset: Open Web Text

Neuron 1874 in Layer 6

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: 3.1981. Min Range: -3.1981

Max Act: 3.1981. Min Act: -0.1700

Data Index: 4818024 (Open Web Text)

Max Activating Token Index: 811

Text #1

Max Range: 3.1981. Min Range: -3.1981

Max Act: 3.1243. Min Act: -0.1700

Data Index: 6192473 (Open Web Text)

Max Activating Token Index: 348

Text #2

Max Range: 3.1981. Min Range: -3.1981

Max Act: 3.0826. Min Act: -0.1700

Data Index: 5155272 (Open Web Text)

Max Activating Token Index: 872

Text #3

Max Range: 3.1981. Min Range: -3.1981

Max Act: 3.0669. Min Act: -0.1700

Data Index: 8063058 (Open Web Text)

Max Activating Token Index: 716

Text #4

Max Range: 3.1981. Min Range: -3.1981

Max Act: 3.0645. Min Act: -0.1700

Data Index: 3588287 (Open Web Text)

Max Activating Token Index: 1002

Text #5

Max Range: 3.1981. Min Range: -3.1981

Max Act: 3.0531. Min Act: -0.1700

Data Index: 589991 (Open Web Text)

Max Activating Token Index: 486

Text #6

Max Range: 3.1981. Min Range: -3.1981

Max Act: 3.0376. Min Act: -0.1700

Data Index: 888767 (Open Web Text)

Max Activating Token Index: 444

Text #7

Max Range: 3.1981. Min Range: -3.1981

Max Act: 3.0354. Min Act: -0.1700

Data Index: 6159521 (Open Web Text)

Max Activating Token Index: 558

Text #8

Max Range: 3.1981. Min Range: -3.1981

Max Act: 3.0372. Min Act: -0.1700

Data Index: 3195034 (Open Web Text)

Max Activating Token Index: 1016

Text #9

Max Range: 3.1981. Min Range: -3.1981

Max Act: 3.0107. Min Act: -0.1700

Data Index: 130399 (Open Web Text)

Max Activating Token Index: 1013

Text #10

Max Range: 3.1981. Min Range: -3.1981

Max Act: 3.0149. Min Act: -0.1700

Data Index: 1883536 (Open Web Text)

Max Activating Token Index: 963

Text #11

Max Range: 3.1981. Min Range: -3.1981

Max Act: 2.9963. Min Act: -0.1700

Data Index: 8669158 (Open Web Text)

Max Activating Token Index: 887

Text #12

Max Range: 3.1981. Min Range: -3.1981

Max Act: 2.9937. Min Act: -0.1700

Data Index: 8060001 (Open Web Text)

Max Activating Token Index: 413

Text #13

Max Range: 3.1981. Min Range: -3.1981

Max Act: 2.9843. Min Act: -0.1700

Data Index: 7553419 (Open Web Text)

Max Activating Token Index: 976

Text #14

Max Range: 3.1981. Min Range: -3.1981

Max Act: 2.9776. Min Act: -0.1700

Data Index: 8020867 (Open Web Text)

Max Activating Token Index: 905

Text #15

Max Range: 3.1981. Min Range: -3.1981

Max Act: 2.9493. Min Act: -0.1700

Data Index: 3977498 (Open Web Text)

Max Activating Token Index: 1021

Text #16

Max Range: 3.1981. Min Range: -3.1981

Max Act: 2.9342. Min Act: -0.1700

Data Index: 5559104 (Open Web Text)

Max Activating Token Index: 533

Text #17

Max Range: 3.1981. Min Range: -3.1981

Max Act: 2.9455. Min Act: -0.1700

Data Index: 594679 (Open Web Text)

Max Activating Token Index: 275

Text #18

Max Range: 3.1981. Min Range: -3.1981

Max Act: 2.9319. Min Act: -0.1700

Data Index: 7310895 (Open Web Text)

Max Activating Token Index: 768

Text #19

Max Range: 3.1981. Min Range: -3.1981

Max Act: 2.9358. Min Act: -0.1700

Data Index: 3142995 (Open Web Text)

Max Activating Token Index: 795