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

Dataset: Open Web Text

Neuron 880 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: 4.0407. Min Range: -4.0407

Max Act: 4.0407. Min Act: -0.1700

Data Index: 5783627 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 4.0407. Min Range: -4.0407

Max Act: 4.0230. Min Act: -0.1700

Data Index: 6242181 (Open Web Text)

Max Activating Token Index: 329

Text #2

Max Range: 4.0407. Min Range: -4.0407

Max Act: 4.0066. Min Act: -0.1700

Data Index: 3141497 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 4.0407. Min Range: -4.0407

Max Act: 3.9855. Min Act: -0.1700

Data Index: 3760908 (Open Web Text)

Max Activating Token Index: 15

Text #4

Max Range: 4.0407. Min Range: -4.0407

Max Act: 3.9818. Min Act: -0.1700

Data Index: 5422542 (Open Web Text)

Max Activating Token Index: 24

Text #5

Max Range: 4.0407. Min Range: -4.0407

Max Act: 3.9894. Min Act: -0.1700

Data Index: 5310157 (Open Web Text)

Max Activating Token Index: 148

Text #6

Max Range: 4.0407. Min Range: -4.0407

Max Act: 3.9875. Min Act: -0.1700

Data Index: 4518792 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.0407. Min Range: -4.0407

Max Act: 3.9608. Min Act: -0.1700

Data Index: 3914712 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 4.0407. Min Range: -4.0407

Max Act: 3.9702. Min Act: -0.1700

Data Index: 1420918 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 4.0407. Min Range: -4.0407

Max Act: 3.9945. Min Act: -0.1700

Data Index: 343134 (Open Web Text)

Max Activating Token Index: 814

Text #10

Max Range: 4.0407. Min Range: -4.0407

Max Act: 3.9721. Min Act: -0.1700

Data Index: 7541658 (Open Web Text)

Max Activating Token Index: 17

Text #11

Max Range: 4.0407. Min Range: -4.0407

Max Act: 3.9406. Min Act: -0.1700

Data Index: 3284673 (Open Web Text)

Max Activating Token Index: 187

Text #12

Max Range: 4.0407. Min Range: -4.0407

Max Act: 3.9512. Min Act: -0.1700

Data Index: 3833877 (Open Web Text)

Max Activating Token Index: 730

Text #13

Max Range: 4.0407. Min Range: -4.0407

Max Act: 3.9652. Min Act: -0.1700

Data Index: 1332981 (Open Web Text)

Max Activating Token Index: 135

Text #14

Max Range: 4.0407. Min Range: -4.0407

Max Act: 3.9513. Min Act: -0.1700

Data Index: 4187358 (Open Web Text)

Max Activating Token Index: 202

Text #15

Max Range: 4.0407. Min Range: -4.0407

Max Act: 3.9581. Min Act: -0.1700

Data Index: 5922397 (Open Web Text)

Max Activating Token Index: 44

Text #16

Max Range: 4.0407. Min Range: -4.0407

Max Act: 3.9301. Min Act: -0.1700

Data Index: 5587855 (Open Web Text)

Max Activating Token Index: 333

Text #17

Max Range: 4.0407. Min Range: -4.0407

Max Act: 3.9454. Min Act: -0.1700

Data Index: 2496391 (Open Web Text)

Max Activating Token Index: 943

Text #18

Max Range: 4.0407. Min Range: -4.0407

Max Act: 3.9494. Min Act: -0.1700

Data Index: 1077954 (Open Web Text)

Max Activating Token Index: 462

Text #19

Max Range: 4.0407. Min Range: -4.0407

Max Act: 3.9432. Min Act: -0.1700

Data Index: 6345684 (Open Web Text)

Max Activating Token Index: 42