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

Dataset: Open Web Text

Neuron 1268 in Layer 1

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: 1.4686. Min Range: -1.4686

Max Act: 1.4686. Min Act: -0.1700

Data Index: 3674685 (Open Web Text)

Max Activating Token Index: 15

Text #1

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.4649. Min Act: -0.1700

Data Index: 3674690 (Open Web Text)

Max Activating Token Index: 22

Text #2

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.4031. Min Act: -0.1700

Data Index: 3674683 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.3649. Min Act: -0.1700

Data Index: 3674695 (Open Web Text)

Max Activating Token Index: 15

Text #4

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.3424. Min Act: -0.1700

Data Index: 7955685 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.3247. Min Act: -0.1700

Data Index: 7765050 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.3276. Min Act: -0.1700

Data Index: 2949988 (Open Web Text)

Max Activating Token Index: 17

Text #7

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.3162. Min Act: -0.1700

Data Index: 2541685 (Open Web Text)

Max Activating Token Index: 21

Text #8

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.3208. Min Act: -0.1700

Data Index: 3681550 (Open Web Text)

Max Activating Token Index: 19

Text #9

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.3267. Min Act: -0.1700

Data Index: 8286983 (Open Web Text)

Max Activating Token Index: 24

Text #10

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.3102. Min Act: -0.1700

Data Index: 3145648 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.3025. Min Act: -0.1700

Data Index: 5536190 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.3128. Min Act: -0.1700

Data Index: 7567368 (Open Web Text)

Max Activating Token Index: 41

Text #13

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.2863. Min Act: -0.1700

Data Index: 7567367 (Open Web Text)

Max Activating Token Index: 37

Text #14

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.2896. Min Act: -0.1700

Data Index: 3674679 (Open Web Text)

Max Activating Token Index: 18

Text #15

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.2754. Min Act: -0.1700

Data Index: 3955132 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.2763. Min Act: -0.1700

Data Index: 8530538 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.2607. Min Act: -0.1700

Data Index: 7567365 (Open Web Text)

Max Activating Token Index: 35

Text #18

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.2745. Min Act: -0.1700

Data Index: 2823902 (Open Web Text)

Max Activating Token Index: 51

Text #19

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.2581. Min Act: -0.1700

Data Index: 3674696 (Open Web Text)

Max Activating Token Index: 40