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

Dataset: Open Web Text

Neuron 571 in Layer 3

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: 1.8505. Min Range: -1.8505

Max Act: 1.8491. Min Act: -0.1699

Data Index: 8398133 (Open Web Text)

Max Activating Token Index: 51

Text #1

Max Range: 1.8505. Min Range: -1.8505

Max Act: 1.8505. Min Act: -0.1699

Data Index: 1972041 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 1.8505. Min Range: -1.8505

Max Act: 1.8300. Min Act: -0.1698

Data Index: 3014960 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 1.8505. Min Range: -1.8505

Max Act: 1.8295. Min Act: -0.1700

Data Index: 499745 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 1.8505. Min Range: -1.8505

Max Act: 1.8225. Min Act: -0.1700

Data Index: 999919 (Open Web Text)

Max Activating Token Index: 1015

Text #5

Max Range: 1.8505. Min Range: -1.8505

Max Act: 1.8316. Min Act: -0.1700

Data Index: 4368136 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 1.8505. Min Range: -1.8505

Max Act: 1.8077. Min Act: -0.1693

Data Index: 3233815 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 1.8505. Min Range: -1.8505

Max Act: 1.8071. Min Act: -0.1700

Data Index: 3347075 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 1.8505. Min Range: -1.8505

Max Act: 1.8092. Min Act: -0.1700

Data Index: 1520706 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 1.8505. Min Range: -1.8505

Max Act: 1.8091. Min Act: -0.1700

Data Index: 1165397 (Open Web Text)

Max Activating Token Index: 669

Text #10

Max Range: 1.8505. Min Range: -1.8505

Max Act: 1.7952. Min Act: -0.1700

Data Index: 3473826 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 1.8505. Min Range: -1.8505

Max Act: 1.7856. Min Act: -0.1700

Data Index: 1497292 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 1.8505. Min Range: -1.8505

Max Act: 1.7828. Min Act: -0.1699

Data Index: 6285633 (Open Web Text)

Max Activating Token Index: 150

Text #13

Max Range: 1.8505. Min Range: -1.8505

Max Act: 1.7944. Min Act: -0.1700

Data Index: 1520910 (Open Web Text)

Max Activating Token Index: 246

Text #14

Max Range: 1.8505. Min Range: -1.8505

Max Act: 1.7913. Min Act: -0.1700

Data Index: 6019051 (Open Web Text)

Max Activating Token Index: 1014

Text #15

Max Range: 1.8505. Min Range: -1.8505

Max Act: 1.7784. Min Act: -0.1700

Data Index: 6362047 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 1.8505. Min Range: -1.8505

Max Act: 1.7777. Min Act: -0.1700

Data Index: 3543114 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 1.8505. Min Range: -1.8505

Max Act: 1.7777. Min Act: -0.1700

Data Index: 6394184 (Open Web Text)

Max Activating Token Index: 142

Text #18

Max Range: 1.8505. Min Range: -1.8505

Max Act: 1.7749. Min Act: -0.1700

Data Index: 2257775 (Open Web Text)

Max Activating Token Index: 47

Text #19

Max Range: 1.8505. Min Range: -1.8505

Max Act: 1.7731. Min Act: -0.1700

Data Index: 3313940 (Open Web Text)

Max Activating Token Index: 245