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

Dataset: Open Web Text

Neuron 2864 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: 1.8662. Min Range: -1.8662

Max Act: 1.8662. Min Act: -0.1700

Data Index: 1828322 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 1.8662. Min Range: -1.8662

Max Act: 1.8449. Min Act: -0.1700

Data Index: 5598029 (Open Web Text)

Max Activating Token Index: 973

Text #2

Max Range: 1.8662. Min Range: -1.8662

Max Act: 1.8259. Min Act: -0.1700

Data Index: 6880868 (Open Web Text)

Max Activating Token Index: 375

Text #3

Max Range: 1.8662. Min Range: -1.8662

Max Act: 1.8236. Min Act: -0.1700

Data Index: 3133418 (Open Web Text)

Max Activating Token Index: 366

Text #4

Max Range: 1.8662. Min Range: -1.8662

Max Act: 1.8013. Min Act: -0.1700

Data Index: 6284631 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.8662. Min Range: -1.8662

Max Act: 1.8177. Min Act: -0.1700

Data Index: 5550892 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 1.8662. Min Range: -1.8662

Max Act: 1.7950. Min Act: -0.1700

Data Index: 701918 (Open Web Text)

Max Activating Token Index: 28

Text #7

Max Range: 1.8662. Min Range: -1.8662

Max Act: 1.7747. Min Act: -0.1700

Data Index: 8660558 (Open Web Text)

Max Activating Token Index: 756

Text #8

Max Range: 1.8662. Min Range: -1.8662

Max Act: 1.7929. Min Act: -0.1700

Data Index: 8249193 (Open Web Text)

Max Activating Token Index: 695

Text #9

Max Range: 1.8662. Min Range: -1.8662

Max Act: 1.7931. Min Act: -0.1700

Data Index: 5826378 (Open Web Text)

Max Activating Token Index: 432

Text #10

Max Range: 1.8662. Min Range: -1.8662

Max Act: 1.7767. Min Act: -0.1700

Data Index: 2298761 (Open Web Text)

Max Activating Token Index: 418

Text #11

Max Range: 1.8662. Min Range: -1.8662

Max Act: 1.7774. Min Act: -0.1700

Data Index: 2867347 (Open Web Text)

Max Activating Token Index: 661

Text #12

Max Range: 1.8662. Min Range: -1.8662

Max Act: 1.7885. Min Act: -0.1700

Data Index: 2058675 (Open Web Text)

Max Activating Token Index: 375

Text #13

Max Range: 1.8662. Min Range: -1.8662

Max Act: 1.7738. Min Act: -0.1700

Data Index: 4687380 (Open Web Text)

Max Activating Token Index: 649

Text #14

Max Range: 1.8662. Min Range: -1.8662

Max Act: 1.7711. Min Act: -0.1700

Data Index: 4784208 (Open Web Text)

Max Activating Token Index: 288

Text #15

Max Range: 1.8662. Min Range: -1.8662

Max Act: 1.7676. Min Act: -0.1700

Data Index: 3457491 (Open Web Text)

Max Activating Token Index: 1002

Text #16

Max Range: 1.8662. Min Range: -1.8662

Max Act: 1.7681. Min Act: -0.1700

Data Index: 4496091 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 1.8662. Min Range: -1.8662

Max Act: 1.7625. Min Act: -0.1700

Data Index: 701917 (Open Web Text)

Max Activating Token Index: 746

Text #18

Max Range: 1.8662. Min Range: -1.8662

Max Act: 1.7529. Min Act: -0.1700

Data Index: 4187517 (Open Web Text)

Max Activating Token Index: 652

Text #19

Max Range: 1.8662. Min Range: -1.8662

Max Act: 1.7636. Min Act: -0.1700

Data Index: 8371090 (Open Web Text)

Max Activating Token Index: 615