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

Dataset: Open Web Text

Neuron 484 in Layer 0

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: 2.9713. Min Range: -2.9713

Max Act: 2.9713. Min Act: -0.1700

Data Index: 2946697 (Open Web Text)

Max Activating Token Index: 822

Text #1

Max Range: 2.9713. Min Range: -2.9713

Max Act: 2.9481. Min Act: -0.1700

Data Index: 1904561 (Open Web Text)

Max Activating Token Index: 277

Text #2

Max Range: 2.9713. Min Range: -2.9713

Max Act: 2.9256. Min Act: -0.1700

Data Index: 6760792 (Open Web Text)

Max Activating Token Index: 412

Text #3

Max Range: 2.9713. Min Range: -2.9713

Max Act: 2.9330. Min Act: -0.1700

Data Index: 1270583 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.9713. Min Range: -2.9713

Max Act: 2.9149. Min Act: -0.1700

Data Index: 1904558 (Open Web Text)

Max Activating Token Index: 132

Text #5

Max Range: 2.9713. Min Range: -2.9713

Max Act: 2.9261. Min Act: -0.1700

Data Index: 1566754 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.9713. Min Range: -2.9713

Max Act: 2.9229. Min Act: -0.1700

Data Index: 4748597 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.9713. Min Range: -2.9713

Max Act: 2.9095. Min Act: -0.1700

Data Index: 1904559 (Open Web Text)

Max Activating Token Index: 103

Text #8

Max Range: 2.9713. Min Range: -2.9713

Max Act: 2.9185. Min Act: -0.1700

Data Index: 4403575 (Open Web Text)

Max Activating Token Index: 270

Text #9

Max Range: 2.9713. Min Range: -2.9713

Max Act: 2.9206. Min Act: -0.1700

Data Index: 198192 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.9713. Min Range: -2.9713

Max Act: 2.9135. Min Act: -0.1700

Data Index: 8227042 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 2.9713. Min Range: -2.9713

Max Act: 2.9063. Min Act: -0.1700

Data Index: 2898949 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.9713. Min Range: -2.9713

Max Act: 2.8946. Min Act: -0.1700

Data Index: 550091 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.9713. Min Range: -2.9713

Max Act: 2.8893. Min Act: -0.1700

Data Index: 8073656 (Open Web Text)

Max Activating Token Index: 620

Text #14

Max Range: 2.9713. Min Range: -2.9713

Max Act: 2.8751. Min Act: -0.1700

Data Index: 4208545 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.9713. Min Range: -2.9713

Max Act: 2.8926. Min Act: -0.1700

Data Index: 4076816 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.9713. Min Range: -2.9713

Max Act: 2.8739. Min Act: -0.1700

Data Index: 5013945 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 2.9713. Min Range: -2.9713

Max Act: 2.8891. Min Act: -0.1700

Data Index: 1005227 (Open Web Text)

Max Activating Token Index: 99

Text #18

Max Range: 2.9713. Min Range: -2.9713

Max Act: 2.8791. Min Act: -0.1700

Data Index: 1904557 (Open Web Text)

Max Activating Token Index: 365

Text #19

Max Range: 2.9713. Min Range: -2.9713

Max Act: 2.8802. Min Act: -0.1700

Data Index: 4448121 (Open Web Text)

Max Activating Token Index: 3