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

Dataset: Open Web Text

Neuron 156 in Layer 1

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: 3.5535. Min Range: -3.5535

Max Act: 3.5535. Min Act: -0.1700

Data Index: 3250722 (Open Web Text)

Max Activating Token Index: 592

Text #1

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.5222. Min Act: -0.1700

Data Index: 3575083 (Open Web Text)

Max Activating Token Index: 181

Text #2

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.5190. Min Act: -0.1700

Data Index: 7544859 (Open Web Text)

Max Activating Token Index: 33

Text #3

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.5181. Min Act: -0.1700

Data Index: 2522403 (Open Web Text)

Max Activating Token Index: 145

Text #4

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.5113. Min Act: -0.1700

Data Index: 2940416 (Open Web Text)

Max Activating Token Index: 629

Text #5

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.4909. Min Act: -0.1700

Data Index: 2735597 (Open Web Text)

Max Activating Token Index: 209

Text #6

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.5005. Min Act: -0.1700

Data Index: 8772902 (Open Web Text)

Max Activating Token Index: 148

Text #7

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.5125. Min Act: -0.1700

Data Index: 3257704 (Open Web Text)

Max Activating Token Index: 66

Text #8

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.4917. Min Act: -0.1700

Data Index: 1900173 (Open Web Text)

Max Activating Token Index: 356

Text #9

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.4885. Min Act: -0.1700

Data Index: 6614019 (Open Web Text)

Max Activating Token Index: 320

Text #10

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.4602. Min Act: -0.1700

Data Index: 6819447 (Open Web Text)

Max Activating Token Index: 49

Text #11

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.4685. Min Act: -0.1700

Data Index: 3900915 (Open Web Text)

Max Activating Token Index: 63

Text #12

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.4542. Min Act: -0.1700

Data Index: 1455215 (Open Web Text)

Max Activating Token Index: 382

Text #13

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.4698. Min Act: -0.1700

Data Index: 4279358 (Open Web Text)

Max Activating Token Index: 433

Text #14

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.4798. Min Act: -0.1700

Data Index: 4482049 (Open Web Text)

Max Activating Token Index: 334

Text #15

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.4749. Min Act: -0.1700

Data Index: 4076129 (Open Web Text)

Max Activating Token Index: 250

Text #16

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.4729. Min Act: -0.1700

Data Index: 852269 (Open Web Text)

Max Activating Token Index: 722

Text #17

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.4815. Min Act: -0.1700

Data Index: 5783428 (Open Web Text)

Max Activating Token Index: 381

Text #18

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.4634. Min Act: -0.1700

Data Index: 5521080 (Open Web Text)

Max Activating Token Index: 762

Text #19

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.4644. Min Act: -0.1700

Data Index: 5065023 (Open Web Text)

Max Activating Token Index: 196