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

Dataset: Open Web Text

Neuron 2363 in Layer 5

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: 4.5802. Min Range: -4.5802

Max Act: 4.5802. Min Act: -0.1700

Data Index: 2233107 (Open Web Text)

Max Activating Token Index: 951

Text #1

Max Range: 4.5802. Min Range: -4.5802

Max Act: 4.5406. Min Act: -0.1700

Data Index: 1549897 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.5802. Min Range: -4.5802

Max Act: 4.4469. Min Act: -0.1700

Data Index: 5469487 (Open Web Text)

Max Activating Token Index: 923

Text #3

Max Range: 4.5802. Min Range: -4.5802

Max Act: 4.4540. Min Act: -0.1700

Data Index: 991658 (Open Web Text)

Max Activating Token Index: 1004

Text #4

Max Range: 4.5802. Min Range: -4.5802

Max Act: 4.4311. Min Act: -0.1700

Data Index: 1265991 (Open Web Text)

Max Activating Token Index: 966

Text #5

Max Range: 4.5802. Min Range: -4.5802

Max Act: 4.4086. Min Act: -0.1700

Data Index: 386295 (Open Web Text)

Max Activating Token Index: 582

Text #6

Max Range: 4.5802. Min Range: -4.5802

Max Act: 4.4079. Min Act: -0.1700

Data Index: 6669739 (Open Web Text)

Max Activating Token Index: 26

Text #7

Max Range: 4.5802. Min Range: -4.5802

Max Act: 4.3951. Min Act: -0.1700

Data Index: 3714849 (Open Web Text)

Max Activating Token Index: 1013

Text #8

Max Range: 4.5802. Min Range: -4.5802

Max Act: 4.4147. Min Act: -0.1700

Data Index: 6657714 (Open Web Text)

Max Activating Token Index: 696

Text #9

Max Range: 4.5802. Min Range: -4.5802

Max Act: 4.3673. Min Act: -0.1700

Data Index: 174974 (Open Web Text)

Max Activating Token Index: 845

Text #10

Max Range: 4.5802. Min Range: -4.5802

Max Act: 4.3491. Min Act: -0.1700

Data Index: 345766 (Open Web Text)

Max Activating Token Index: 372

Text #11

Max Range: 4.5802. Min Range: -4.5802

Max Act: 4.3767. Min Act: -0.1700

Data Index: 8741966 (Open Web Text)

Max Activating Token Index: 828

Text #12

Max Range: 4.5802. Min Range: -4.5802

Max Act: 4.3575. Min Act: -0.1700

Data Index: 8504421 (Open Web Text)

Max Activating Token Index: 864

Text #13

Max Range: 4.5802. Min Range: -4.5802

Max Act: 4.3935. Min Act: -0.1700

Data Index: 8213715 (Open Web Text)

Max Activating Token Index: 418

Text #14

Max Range: 4.5802. Min Range: -4.5802

Max Act: 4.3588. Min Act: -0.1700

Data Index: 6853393 (Open Web Text)

Max Activating Token Index: 919

Text #15

Max Range: 4.5802. Min Range: -4.5802

Max Act: 4.3625. Min Act: -0.1700

Data Index: 4600400 (Open Web Text)

Max Activating Token Index: 768

Text #16

Max Range: 4.5802. Min Range: -4.5802

Max Act: 4.3580. Min Act: -0.1700

Data Index: 6001570 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 4.5802. Min Range: -4.5802

Max Act: 4.3582. Min Act: -0.1700

Data Index: 5574407 (Open Web Text)

Max Activating Token Index: 130

Text #18

Max Range: 4.5802. Min Range: -4.5802

Max Act: 4.3450. Min Act: -0.1700

Data Index: 7244712 (Open Web Text)

Max Activating Token Index: 447

Text #19

Max Range: 4.5802. Min Range: -4.5802

Max Act: 4.3220. Min Act: -0.1700

Data Index: 1700570 (Open Web Text)

Max Activating Token Index: 863