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

Dataset: Open Web Text

Neuron 1608 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: 3.8898. Min Range: -3.8898

Max Act: 3.8749. Min Act: -0.1700

Data Index: 4685021 (Open Web Text)

Max Activating Token Index: 890

Text #1

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.8898. Min Act: -0.1700

Data Index: 583590 (Open Web Text)

Max Activating Token Index: 857

Text #2

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.8443. Min Act: -0.1700

Data Index: 7104559 (Open Web Text)

Max Activating Token Index: 41

Text #3

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.8194. Min Act: -0.1700

Data Index: 111349 (Open Web Text)

Max Activating Token Index: 110

Text #4

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.7616. Min Act: -0.1700

Data Index: 1225729 (Open Web Text)

Max Activating Token Index: 1020

Text #5

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.7471. Min Act: -0.1700

Data Index: 2054341 (Open Web Text)

Max Activating Token Index: 207

Text #6

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.7782. Min Act: -0.1700

Data Index: 2055289 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.7528. Min Act: -0.1700

Data Index: 7884139 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.7329. Min Act: -0.1700

Data Index: 1269958 (Open Web Text)

Max Activating Token Index: 801

Text #9

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.7643. Min Act: -0.1700

Data Index: 1569910 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.7368. Min Act: -0.1700

Data Index: 614517 (Open Web Text)

Max Activating Token Index: 969

Text #11

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.6845. Min Act: -0.1700

Data Index: 2703616 (Open Web Text)

Max Activating Token Index: 464

Text #12

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.7502. Min Act: -0.1700

Data Index: 1332142 (Open Web Text)

Max Activating Token Index: 181

Text #13

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.7564. Min Act: -0.1700

Data Index: 2490202 (Open Web Text)

Max Activating Token Index: 383

Text #14

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.7251. Min Act: -0.1700

Data Index: 4563145 (Open Web Text)

Max Activating Token Index: 755

Text #15

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.6975. Min Act: -0.1700

Data Index: 7491563 (Open Web Text)

Max Activating Token Index: 893

Text #16

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.7764. Min Act: -0.1700

Data Index: 7365561 (Open Web Text)

Max Activating Token Index: 311

Text #17

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.7131. Min Act: -0.1700

Data Index: 4629347 (Open Web Text)

Max Activating Token Index: 713

Text #18

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.7037. Min Act: -0.1700

Data Index: 2658002 (Open Web Text)

Max Activating Token Index: 893

Text #19

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.6869. Min Act: -0.1700

Data Index: 5988913 (Open Web Text)

Max Activating Token Index: 575