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

Dataset: Open Web Text

Neuron 1700 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: 4.1440. Min Range: -4.1440

Max Act: 4.1440. Min Act: -0.1700

Data Index: 5391328 (Open Web Text)

Max Activating Token Index: 199

Text #1

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.8775. Min Act: -0.1700

Data Index: 1879697 (Open Web Text)

Max Activating Token Index: 128

Text #2

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.8841. Min Act: -0.1700

Data Index: 731056 (Open Web Text)

Max Activating Token Index: 904

Text #3

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.8688. Min Act: -0.1700

Data Index: 1734808 (Open Web Text)

Max Activating Token Index: 699

Text #4

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.8673. Min Act: -0.1700

Data Index: 3229645 (Open Web Text)

Max Activating Token Index: 682

Text #5

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.8738. Min Act: -0.1700

Data Index: 6723999 (Open Web Text)

Max Activating Token Index: 824

Text #6

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.8254. Min Act: -0.1700

Data Index: 2554414 (Open Web Text)

Max Activating Token Index: 777

Text #7

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.8349. Min Act: -0.1700

Data Index: 4367081 (Open Web Text)

Max Activating Token Index: 663

Text #8

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.8517. Min Act: -0.1700

Data Index: 3026408 (Open Web Text)

Max Activating Token Index: 561

Text #9

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.8360. Min Act: -0.1700

Data Index: 4271275 (Open Web Text)

Max Activating Token Index: 636

Text #10

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.8377. Min Act: -0.1700

Data Index: 7734765 (Open Web Text)

Max Activating Token Index: 63

Text #11

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.8429. Min Act: -0.1700

Data Index: 4550130 (Open Web Text)

Max Activating Token Index: 444

Text #12

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.8343. Min Act: -0.1700

Data Index: 1995863 (Open Web Text)

Max Activating Token Index: 883

Text #13

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.7984. Min Act: -0.1700

Data Index: 6015913 (Open Web Text)

Max Activating Token Index: 23

Text #14

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.7889. Min Act: -0.1700

Data Index: 4600138 (Open Web Text)

Max Activating Token Index: 943

Text #15

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.8198. Min Act: -0.1700

Data Index: 1713101 (Open Web Text)

Max Activating Token Index: 124

Text #16

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.7598. Min Act: -0.1700

Data Index: 4124351 (Open Web Text)

Max Activating Token Index: 278

Text #17

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.7639. Min Act: -0.1700

Data Index: 4135086 (Open Web Text)

Max Activating Token Index: 220

Text #18

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.7829. Min Act: -0.1700

Data Index: 2078736 (Open Web Text)

Max Activating Token Index: 240

Text #19

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.7629. Min Act: -0.1700

Data Index: 6344736 (Open Web Text)

Max Activating Token Index: 955