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

Dataset: Open Web Text

Neuron 1689 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: 3.1367. Min Range: -3.1367

Max Act: 3.1367. Min Act: -0.1700

Data Index: 2201620 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.1311. Min Act: -0.1700

Data Index: 8557768 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.1183. Min Act: -0.1700

Data Index: 692642 (Open Web Text)

Max Activating Token Index: 234

Text #3

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.1188. Min Act: -0.1700

Data Index: 4700457 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0974. Min Act: -0.1700

Data Index: 5324817 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.1076. Min Act: -0.1700

Data Index: 4343947 (Open Web Text)

Max Activating Token Index: 257

Text #6

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0853. Min Act: -0.1700

Data Index: 6202392 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0919. Min Act: -0.1700

Data Index: 3034700 (Open Web Text)

Max Activating Token Index: 460

Text #8

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0875. Min Act: -0.1700

Data Index: 1704543 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0925. Min Act: -0.1700

Data Index: 2421455 (Open Web Text)

Max Activating Token Index: 302

Text #10

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0879. Min Act: -0.1700

Data Index: 5593296 (Open Web Text)

Max Activating Token Index: 395

Text #11

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0838. Min Act: -0.1700

Data Index: 3306368 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0738. Min Act: -0.1700

Data Index: 8123211 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0753. Min Act: -0.1700

Data Index: 4129652 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0622. Min Act: -0.1700

Data Index: 2935456 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0515. Min Act: -0.1700

Data Index: 3020503 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0637. Min Act: -0.1700

Data Index: 876654 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0646. Min Act: -0.1700

Data Index: 5381770 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0564. Min Act: -0.1700

Data Index: 1677053 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0598. Min Act: -0.1700

Data Index: 3024610 (Open Web Text)

Max Activating Token Index: 8