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

Dataset: Open Web Text

Neuron 157 in Layer 6

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: 5.5694. Min Range: -5.5694

Max Act: 5.5694. Min Act: -0.1700

Data Index: 6134575 (Open Web Text)

Max Activating Token Index: 775

Text #1

Max Range: 5.5694. Min Range: -5.5694

Max Act: 5.5105. Min Act: -0.1700

Data Index: 2170228 (Open Web Text)

Max Activating Token Index: 951

Text #2

Max Range: 5.5694. Min Range: -5.5694

Max Act: 5.3972. Min Act: -0.1700

Data Index: 4599843 (Open Web Text)

Max Activating Token Index: 432

Text #3

Max Range: 5.5694. Min Range: -5.5694

Max Act: 5.4003. Min Act: -0.1700

Data Index: 2861984 (Open Web Text)

Max Activating Token Index: 991

Text #4

Max Range: 5.5694. Min Range: -5.5694

Max Act: 5.3644. Min Act: -0.1700

Data Index: 6222646 (Open Web Text)

Max Activating Token Index: 328

Text #5

Max Range: 5.5694. Min Range: -5.5694

Max Act: 5.3578. Min Act: -0.1700

Data Index: 3450216 (Open Web Text)

Max Activating Token Index: 844

Text #6

Max Range: 5.5694. Min Range: -5.5694

Max Act: 5.3718. Min Act: -0.1700

Data Index: 3664701 (Open Web Text)

Max Activating Token Index: 185

Text #7

Max Range: 5.5694. Min Range: -5.5694

Max Act: 5.3054. Min Act: -0.1700

Data Index: 4802211 (Open Web Text)

Max Activating Token Index: 966

Text #8

Max Range: 5.5694. Min Range: -5.5694

Max Act: 5.3067. Min Act: -0.1700

Data Index: 7971715 (Open Web Text)

Max Activating Token Index: 768

Text #9

Max Range: 5.5694. Min Range: -5.5694

Max Act: 5.3214. Min Act: -0.1700

Data Index: 4326039 (Open Web Text)

Max Activating Token Index: 698

Text #10

Max Range: 5.5694. Min Range: -5.5694

Max Act: 5.2663. Min Act: -0.1700

Data Index: 8768597 (Open Web Text)

Max Activating Token Index: 283

Text #11

Max Range: 5.5694. Min Range: -5.5694

Max Act: 5.2902. Min Act: -0.1700

Data Index: 1038141 (Open Web Text)

Max Activating Token Index: 836

Text #12

Max Range: 5.5694. Min Range: -5.5694

Max Act: 5.3162. Min Act: -0.1700

Data Index: 8064489 (Open Web Text)

Max Activating Token Index: 355

Text #13

Max Range: 5.5694. Min Range: -5.5694

Max Act: 5.2551. Min Act: -0.1700

Data Index: 918398 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 5.5694. Min Range: -5.5694

Max Act: 5.2315. Min Act: -0.1700

Data Index: 3579978 (Open Web Text)

Max Activating Token Index: 763

Text #15

Max Range: 5.5694. Min Range: -5.5694

Max Act: 5.2624. Min Act: -0.1700

Data Index: 6241279 (Open Web Text)

Max Activating Token Index: 931

Text #16

Max Range: 5.5694. Min Range: -5.5694

Max Act: 5.2552. Min Act: -0.1700

Data Index: 5768744 (Open Web Text)

Max Activating Token Index: 929

Text #17

Max Range: 5.5694. Min Range: -5.5694

Max Act: 5.2612. Min Act: -0.1700

Data Index: 5482238 (Open Web Text)

Max Activating Token Index: 847

Text #18

Max Range: 5.5694. Min Range: -5.5694

Max Act: 5.2684. Min Act: -0.1700

Data Index: 7198704 (Open Web Text)

Max Activating Token Index: 670

Text #19

Max Range: 5.5694. Min Range: -5.5694

Max Act: 5.2588. Min Act: -0.1700

Data Index: 5074891 (Open Web Text)

Max Activating Token Index: 988