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

Dataset: Open Web Text

Neuron 2889 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: 3.1766. Min Range: -3.1766

Max Act: 3.1766. Min Act: -0.1700

Data Index: 4427751 (Open Web Text)

Max Activating Token Index: 640

Text #1

Max Range: 3.1766. Min Range: -3.1766

Max Act: 3.0778. Min Act: -0.1700

Data Index: 892863 (Open Web Text)

Max Activating Token Index: 173

Text #2

Max Range: 3.1766. Min Range: -3.1766

Max Act: 3.0411. Min Act: -0.1700

Data Index: 3500105 (Open Web Text)

Max Activating Token Index: 565

Text #3

Max Range: 3.1766. Min Range: -3.1766

Max Act: 3.0467. Min Act: -0.1700

Data Index: 2065089 (Open Web Text)

Max Activating Token Index: 669

Text #4

Max Range: 3.1766. Min Range: -3.1766

Max Act: 3.0153. Min Act: -0.1700

Data Index: 6228291 (Open Web Text)

Max Activating Token Index: 779

Text #5

Max Range: 3.1766. Min Range: -3.1766

Max Act: 3.0071. Min Act: -0.1700

Data Index: 8646608 (Open Web Text)

Max Activating Token Index: 636

Text #6

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.9751. Min Act: -0.1700

Data Index: 7177772 (Open Web Text)

Max Activating Token Index: 294

Text #7

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.9414. Min Act: -0.1700

Data Index: 3944249 (Open Web Text)

Max Activating Token Index: 556

Text #8

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.9033. Min Act: -0.1700

Data Index: 6358694 (Open Web Text)

Max Activating Token Index: 731

Text #9

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.9377. Min Act: -0.1700

Data Index: 8673508 (Open Web Text)

Max Activating Token Index: 83

Text #10

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.9186. Min Act: -0.1700

Data Index: 2390136 (Open Web Text)

Max Activating Token Index: 368

Text #11

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.8984. Min Act: -0.1700

Data Index: 7328406 (Open Web Text)

Max Activating Token Index: 718

Text #12

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.8950. Min Act: -0.1700

Data Index: 6682897 (Open Web Text)

Max Activating Token Index: 886

Text #13

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.8875. Min Act: -0.1700

Data Index: 8629422 (Open Web Text)

Max Activating Token Index: 39

Text #14

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.8819. Min Act: -0.1700

Data Index: 2862592 (Open Web Text)

Max Activating Token Index: 199

Text #15

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.8592. Min Act: -0.1700

Data Index: 2346048 (Open Web Text)

Max Activating Token Index: 493

Text #16

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.8847. Min Act: -0.1700

Data Index: 154016 (Open Web Text)

Max Activating Token Index: 400

Text #17

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.8472. Min Act: -0.1700

Data Index: 3222703 (Open Web Text)

Max Activating Token Index: 684

Text #18

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.8758. Min Act: -0.1700

Data Index: 899568 (Open Web Text)

Max Activating Token Index: 581

Text #19

Max Range: 3.1766. Min Range: -3.1766

Max Act: 2.8416. Min Act: -0.1700

Data Index: 2013976 (Open Web Text)

Max Activating Token Index: 177