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

Dataset: Open Web Text

Neuron 2940 in Layer 2

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: 3.2836. Min Range: -3.2836

Max Act: 3.2836. Min Act: -0.1700

Data Index: 5180020 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.2836. Min Range: -3.2836

Max Act: 3.2809. Min Act: -0.1700

Data Index: 1424322 (Open Web Text)

Max Activating Token Index: 49

Text #2

Max Range: 3.2836. Min Range: -3.2836

Max Act: 3.2487. Min Act: -0.1700

Data Index: 1123717 (Open Web Text)

Max Activating Token Index: 367

Text #3

Max Range: 3.2836. Min Range: -3.2836

Max Act: 3.2352. Min Act: -0.1700

Data Index: 8667677 (Open Web Text)

Max Activating Token Index: 559

Text #4

Max Range: 3.2836. Min Range: -3.2836

Max Act: 3.2596. Min Act: -0.1700

Data Index: 2576381 (Open Web Text)

Max Activating Token Index: 319

Text #5

Max Range: 3.2836. Min Range: -3.2836

Max Act: 3.2480. Min Act: -0.1700

Data Index: 6736423 (Open Web Text)

Max Activating Token Index: 901

Text #6

Max Range: 3.2836. Min Range: -3.2836

Max Act: 3.2375. Min Act: -0.1700

Data Index: 7451805 (Open Web Text)

Max Activating Token Index: 723

Text #7

Max Range: 3.2836. Min Range: -3.2836

Max Act: 3.2421. Min Act: -0.1700

Data Index: 8080814 (Open Web Text)

Max Activating Token Index: 883

Text #8

Max Range: 3.2836. Min Range: -3.2836

Max Act: 3.2209. Min Act: -0.1700

Data Index: 473357 (Open Web Text)

Max Activating Token Index: 593

Text #9

Max Range: 3.2836. Min Range: -3.2836

Max Act: 3.2574. Min Act: -0.1700

Data Index: 6609959 (Open Web Text)

Max Activating Token Index: 829

Text #10

Max Range: 3.2836. Min Range: -3.2836

Max Act: 3.2404. Min Act: -0.1700

Data Index: 4954489 (Open Web Text)

Max Activating Token Index: 114

Text #11

Max Range: 3.2836. Min Range: -3.2836

Max Act: 3.2422. Min Act: -0.1700

Data Index: 354398 (Open Web Text)

Max Activating Token Index: 316

Text #12

Max Range: 3.2836. Min Range: -3.2836

Max Act: 3.2644. Min Act: -0.1700

Data Index: 1726000 (Open Web Text)

Max Activating Token Index: 418

Text #13

Max Range: 3.2836. Min Range: -3.2836

Max Act: 3.2646. Min Act: -0.1700

Data Index: 8609180 (Open Web Text)

Max Activating Token Index: 639

Text #14

Max Range: 3.2836. Min Range: -3.2836

Max Act: 3.2135. Min Act: -0.1700

Data Index: 8566103 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.2836. Min Range: -3.2836

Max Act: 3.2425. Min Act: -0.1700

Data Index: 2754208 (Open Web Text)

Max Activating Token Index: 440

Text #16

Max Range: 3.2836. Min Range: -3.2836

Max Act: 3.2034. Min Act: -0.1700

Data Index: 6080918 (Open Web Text)

Max Activating Token Index: 465

Text #17

Max Range: 3.2836. Min Range: -3.2836

Max Act: 3.2291. Min Act: -0.1700

Data Index: 399871 (Open Web Text)

Max Activating Token Index: 309

Text #18

Max Range: 3.2836. Min Range: -3.2836

Max Act: 3.2208. Min Act: -0.1700

Data Index: 1713685 (Open Web Text)

Max Activating Token Index: 442

Text #19

Max Range: 3.2836. Min Range: -3.2836

Max Act: 3.2163. Min Act: -0.1700

Data Index: 6922008 (Open Web Text)

Max Activating Token Index: 428