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

Dataset: Open Web Text

Neuron 2177 in Layer 0

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: 3.0936. Min Range: -3.0936

Max Act: 3.0936. Min Act: -0.1700

Data Index: 2250724 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.0936. Min Range: -3.0936

Max Act: 3.0759. Min Act: -0.1700

Data Index: 2488486 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.0936. Min Range: -3.0936

Max Act: 3.0562. Min Act: -0.1700

Data Index: 2172570 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.0936. Min Range: -3.0936

Max Act: 3.0341. Min Act: -0.1700

Data Index: 8117123 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.0936. Min Range: -3.0936

Max Act: 3.0130. Min Act: -0.1700

Data Index: 2387488 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.9896. Min Act: -0.1700

Data Index: 6843335 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.9962. Min Act: -0.1700

Data Index: 2489659 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.9896. Min Act: -0.1700

Data Index: 3436514 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.9851. Min Act: -0.1700

Data Index: 342532 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.9893. Min Act: -0.1700

Data Index: 8033216 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.9644. Min Act: -0.1700

Data Index: 6457231 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.9728. Min Act: -0.1700

Data Index: 8477240 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.9659. Min Act: -0.1700

Data Index: 6243154 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.9699. Min Act: -0.1700

Data Index: 1058692 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.9616. Min Act: -0.1700

Data Index: 7406232 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.9545. Min Act: -0.1700

Data Index: 2645006 (Open Web Text)

Max Activating Token Index: 13

Text #16

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.9488. Min Act: -0.1700

Data Index: 3338374 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.9524. Min Act: -0.1700

Data Index: 72491 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.9509. Min Act: -0.1700

Data Index: 3715184 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.9493. Min Act: -0.1700

Data Index: 6879785 (Open Web Text)

Max Activating Token Index: 6