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

Dataset: Open Web Text

Neuron 675 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: 3.4285. Min Range: -3.4285

Max Act: 3.4285. Min Act: -0.1700

Data Index: 4301231 (Open Web Text)

Max Activating Token Index: 1020

Text #1

Max Range: 3.4285. Min Range: -3.4285

Max Act: 3.4166. Min Act: -0.1700

Data Index: 6856173 (Open Web Text)

Max Activating Token Index: 699

Text #2

Max Range: 3.4285. Min Range: -3.4285

Max Act: 3.3403. Min Act: -0.1700

Data Index: 622671 (Open Web Text)

Max Activating Token Index: 837

Text #3

Max Range: 3.4285. Min Range: -3.4285

Max Act: 3.3539. Min Act: -0.1700

Data Index: 8533485 (Open Web Text)

Max Activating Token Index: 147

Text #4

Max Range: 3.4285. Min Range: -3.4285

Max Act: 3.2666. Min Act: -0.1700

Data Index: 754254 (Open Web Text)

Max Activating Token Index: 981

Text #5

Max Range: 3.4285. Min Range: -3.4285

Max Act: 3.2694. Min Act: -0.1700

Data Index: 5825830 (Open Web Text)

Max Activating Token Index: 772

Text #6

Max Range: 3.4285. Min Range: -3.4285

Max Act: 3.2426. Min Act: -0.1700

Data Index: 1620158 (Open Web Text)

Max Activating Token Index: 1021

Text #7

Max Range: 3.4285. Min Range: -3.4285

Max Act: 3.2509. Min Act: -0.1700

Data Index: 3846002 (Open Web Text)

Max Activating Token Index: 669

Text #8

Max Range: 3.4285. Min Range: -3.4285

Max Act: 3.2002. Min Act: -0.1700

Data Index: 5732358 (Open Web Text)

Max Activating Token Index: 188

Text #9

Max Range: 3.4285. Min Range: -3.4285

Max Act: 3.1934. Min Act: -0.1700

Data Index: 3505724 (Open Web Text)

Max Activating Token Index: 744

Text #10

Max Range: 3.4285. Min Range: -3.4285

Max Act: 3.1933. Min Act: -0.1700

Data Index: 34331 (Open Web Text)

Max Activating Token Index: 122

Text #11

Max Range: 3.4285. Min Range: -3.4285

Max Act: 3.1896. Min Act: -0.1700

Data Index: 3159676 (Open Web Text)

Max Activating Token Index: 76

Text #12

Max Range: 3.4285. Min Range: -3.4285

Max Act: 3.1790. Min Act: -0.1700

Data Index: 2883793 (Open Web Text)

Max Activating Token Index: 267

Text #13

Max Range: 3.4285. Min Range: -3.4285

Max Act: 3.2009. Min Act: -0.1700

Data Index: 6322119 (Open Web Text)

Max Activating Token Index: 929

Text #14

Max Range: 3.4285. Min Range: -3.4285

Max Act: 3.2120. Min Act: -0.1700

Data Index: 8356941 (Open Web Text)

Max Activating Token Index: 820

Text #15

Max Range: 3.4285. Min Range: -3.4285

Max Act: 3.1903. Min Act: -0.1700

Data Index: 4242350 (Open Web Text)

Max Activating Token Index: 479

Text #16

Max Range: 3.4285. Min Range: -3.4285

Max Act: 3.1815. Min Act: -0.1700

Data Index: 4695272 (Open Web Text)

Max Activating Token Index: 811

Text #17

Max Range: 3.4285. Min Range: -3.4285

Max Act: 3.1808. Min Act: -0.1700

Data Index: 995920 (Open Web Text)

Max Activating Token Index: 736

Text #18

Max Range: 3.4285. Min Range: -3.4285

Max Act: 3.1883. Min Act: -0.1700

Data Index: 8746625 (Open Web Text)

Max Activating Token Index: 285

Text #19

Max Range: 3.4285. Min Range: -3.4285

Max Act: 3.1903. Min Act: -0.1700

Data Index: 3912153 (Open Web Text)

Max Activating Token Index: 333