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

Dataset: Open Web Text

Neuron 1023 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: 4.0621. Min Range: -4.0621

Max Act: 4.0621. Min Act: -0.1700

Data Index: 3911419 (Open Web Text)

Max Activating Token Index: 356

Text #1

Max Range: 4.0621. Min Range: -4.0621

Max Act: 3.9284. Min Act: -0.1700

Data Index: 951274 (Open Web Text)

Max Activating Token Index: 513

Text #2

Max Range: 4.0621. Min Range: -4.0621

Max Act: 3.9264. Min Act: -0.1700

Data Index: 750882 (Open Web Text)

Max Activating Token Index: 613

Text #3

Max Range: 4.0621. Min Range: -4.0621

Max Act: 3.8663. Min Act: -0.1700

Data Index: 333928 (Open Web Text)

Max Activating Token Index: 479

Text #4

Max Range: 4.0621. Min Range: -4.0621

Max Act: 3.9019. Min Act: -0.1700

Data Index: 2623022 (Open Web Text)

Max Activating Token Index: 586

Text #5

Max Range: 4.0621. Min Range: -4.0621

Max Act: 3.8592. Min Act: -0.1700

Data Index: 1398306 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.0621. Min Range: -4.0621

Max Act: 3.8959. Min Act: -0.1700

Data Index: 7826560 (Open Web Text)

Max Activating Token Index: 318

Text #7

Max Range: 4.0621. Min Range: -4.0621

Max Act: 3.8828. Min Act: -0.1700

Data Index: 1309544 (Open Web Text)

Max Activating Token Index: 272

Text #8

Max Range: 4.0621. Min Range: -4.0621

Max Act: 3.8226. Min Act: -0.1700

Data Index: 4226390 (Open Web Text)

Max Activating Token Index: 656

Text #9

Max Range: 4.0621. Min Range: -4.0621

Max Act: 3.8306. Min Act: -0.1700

Data Index: 7456889 (Open Web Text)

Max Activating Token Index: 550

Text #10

Max Range: 4.0621. Min Range: -4.0621

Max Act: 3.8389. Min Act: -0.1700

Data Index: 7126599 (Open Web Text)

Max Activating Token Index: 974

Text #11

Max Range: 4.0621. Min Range: -4.0621

Max Act: 3.8107. Min Act: -0.1700

Data Index: 1087135 (Open Web Text)

Max Activating Token Index: 793

Text #12

Max Range: 4.0621. Min Range: -4.0621

Max Act: 3.8298. Min Act: -0.1700

Data Index: 8417958 (Open Web Text)

Max Activating Token Index: 174

Text #13

Max Range: 4.0621. Min Range: -4.0621

Max Act: 3.8569. Min Act: -0.1700

Data Index: 8182245 (Open Web Text)

Max Activating Token Index: 23

Text #14

Max Range: 4.0621. Min Range: -4.0621

Max Act: 3.8205. Min Act: -0.1700

Data Index: 3081306 (Open Web Text)

Max Activating Token Index: 595

Text #15

Max Range: 4.0621. Min Range: -4.0621

Max Act: 3.8698. Min Act: -0.1700

Data Index: 5722748 (Open Web Text)

Max Activating Token Index: 1009

Text #16

Max Range: 4.0621. Min Range: -4.0621

Max Act: 3.8502. Min Act: -0.1700

Data Index: 5714510 (Open Web Text)

Max Activating Token Index: 334

Text #17

Max Range: 4.0621. Min Range: -4.0621

Max Act: 3.8256. Min Act: -0.1700

Data Index: 5643086 (Open Web Text)

Max Activating Token Index: 904

Text #18

Max Range: 4.0621. Min Range: -4.0621

Max Act: 3.8391. Min Act: -0.1700

Data Index: 6245353 (Open Web Text)

Max Activating Token Index: 626

Text #19

Max Range: 4.0621. Min Range: -4.0621

Max Act: 3.8066. Min Act: -0.1700

Data Index: 7542874 (Open Web Text)

Max Activating Token Index: 879