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

Dataset: Open Web Text

Neuron 807 in Layer 1

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: 1.7648. Min Range: -1.7648

Max Act: 1.7648. Min Act: -0.1700

Data Index: 8491681 (Open Web Text)

Max Activating Token Index: 19

Text #1

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.7635. Min Act: -0.1700

Data Index: 504768 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.7109. Min Act: -0.1700

Data Index: 3820354 (Open Web Text)

Max Activating Token Index: 15

Text #3

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6958. Min Act: -0.1700

Data Index: 3090056 (Open Web Text)

Max Activating Token Index: 63

Text #4

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6920. Min Act: -0.1700

Data Index: 2014110 (Open Web Text)

Max Activating Token Index: 123

Text #5

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6863. Min Act: -0.1699

Data Index: 2969320 (Open Web Text)

Max Activating Token Index: 14

Text #6

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6801. Min Act: -0.1700

Data Index: 4965898 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6679. Min Act: -0.1697

Data Index: 5547321 (Open Web Text)

Max Activating Token Index: 44

Text #8

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6616. Min Act: -0.1700

Data Index: 1979807 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6506. Min Act: -0.1700

Data Index: 8202848 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6505. Min Act: -0.1700

Data Index: 6935543 (Open Web Text)

Max Activating Token Index: 86

Text #11

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6653. Min Act: -0.1700

Data Index: 7234055 (Open Web Text)

Max Activating Token Index: 652

Text #12

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6575. Min Act: -0.1700

Data Index: 2088456 (Open Web Text)

Max Activating Token Index: 25

Text #13

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6414. Min Act: -0.1699

Data Index: 2236922 (Open Web Text)

Max Activating Token Index: 19

Text #14

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6476. Min Act: -0.1700

Data Index: 25756 (Open Web Text)

Max Activating Token Index: 43

Text #15

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6373. Min Act: -0.1700

Data Index: 5687968 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6430. Min Act: -0.1700

Data Index: 7961176 (Open Web Text)

Max Activating Token Index: 68

Text #17

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6476. Min Act: -0.1700

Data Index: 2552507 (Open Web Text)

Max Activating Token Index: 465

Text #18

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6355. Min Act: -0.1700

Data Index: 7721397 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6371. Min Act: -0.1700

Data Index: 3098674 (Open Web Text)

Max Activating Token Index: 11