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

Dataset: Open Web Text

Neuron 1985 in Layer 3

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: 3.5041. Min Range: -3.5041

Max Act: 3.5041. Min Act: -0.1700

Data Index: 218654 (Open Web Text)

Max Activating Token Index: 874

Text #1

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.4213. Min Act: -0.1700

Data Index: 7053441 (Open Web Text)

Max Activating Token Index: 631

Text #2

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3799. Min Act: -0.1700

Data Index: 2269269 (Open Web Text)

Max Activating Token Index: 393

Text #3

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3707. Min Act: -0.1700

Data Index: 3436544 (Open Web Text)

Max Activating Token Index: 472

Text #4

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3165. Min Act: -0.1700

Data Index: 2836990 (Open Web Text)

Max Activating Token Index: 514

Text #5

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3806. Min Act: -0.1700

Data Index: 4805163 (Open Web Text)

Max Activating Token Index: 604

Text #6

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.2986. Min Act: -0.1700

Data Index: 2021655 (Open Web Text)

Max Activating Token Index: 785

Text #7

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3259. Min Act: -0.1700

Data Index: 1963925 (Open Web Text)

Max Activating Token Index: 524

Text #8

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.2727. Min Act: -0.1700

Data Index: 1116304 (Open Web Text)

Max Activating Token Index: 453

Text #9

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.2817. Min Act: -0.1700

Data Index: 697036 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.2959. Min Act: -0.1700

Data Index: 7261111 (Open Web Text)

Max Activating Token Index: 302

Text #11

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.2922. Min Act: -0.1700

Data Index: 3732381 (Open Web Text)

Max Activating Token Index: 243

Text #12

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.2801. Min Act: -0.1700

Data Index: 969704 (Open Web Text)

Max Activating Token Index: 781

Text #13

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.2376. Min Act: -0.1700

Data Index: 6736314 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.2676. Min Act: -0.1700

Data Index: 1902694 (Open Web Text)

Max Activating Token Index: 1010

Text #15

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.2833. Min Act: -0.1700

Data Index: 2510030 (Open Web Text)

Max Activating Token Index: 676

Text #16

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.2525. Min Act: -0.1700

Data Index: 5969213 (Open Web Text)

Max Activating Token Index: 758

Text #17

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.2388. Min Act: -0.1700

Data Index: 4915829 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.2392. Min Act: -0.1700

Data Index: 5429475 (Open Web Text)

Max Activating Token Index: 909

Text #19

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.2447. Min Act: -0.1700

Data Index: 5573443 (Open Web Text)

Max Activating Token Index: 4