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

Dataset: Open Web Text

Neuron 1450 in Layer 5

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: 3.6712. Min Range: -3.6712

Max Act: 3.6712. Min Act: -0.1700

Data Index: 2903153 (Open Web Text)

Max Activating Token Index: 968

Text #1

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6571. Min Act: -0.1700

Data Index: 7186806 (Open Web Text)

Max Activating Token Index: 841

Text #2

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6704. Min Act: -0.1700

Data Index: 8064409 (Open Web Text)

Max Activating Token Index: 924

Text #3

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6586. Min Act: -0.1700

Data Index: 4785386 (Open Web Text)

Max Activating Token Index: 632

Text #4

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6331. Min Act: -0.1700

Data Index: 4674456 (Open Web Text)

Max Activating Token Index: 408

Text #5

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6333. Min Act: -0.1700

Data Index: 3496922 (Open Web Text)

Max Activating Token Index: 441

Text #6

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6272. Min Act: -0.1700

Data Index: 4529391 (Open Web Text)

Max Activating Token Index: 380

Text #7

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6162. Min Act: -0.1700

Data Index: 8357040 (Open Web Text)

Max Activating Token Index: 340

Text #8

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6132. Min Act: -0.1700

Data Index: 8578311 (Open Web Text)

Max Activating Token Index: 430

Text #9

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6131. Min Act: -0.1700

Data Index: 5978899 (Open Web Text)

Max Activating Token Index: 841

Text #10

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6038. Min Act: -0.1700

Data Index: 6297458 (Open Web Text)

Max Activating Token Index: 254

Text #11

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6169. Min Act: -0.1700

Data Index: 186196 (Open Web Text)

Max Activating Token Index: 995

Text #12

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.5899. Min Act: -0.1700

Data Index: 8093767 (Open Web Text)

Max Activating Token Index: 510

Text #13

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6102. Min Act: -0.1700

Data Index: 4969680 (Open Web Text)

Max Activating Token Index: 554

Text #14

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.5983. Min Act: -0.1700

Data Index: 8654264 (Open Web Text)

Max Activating Token Index: 501

Text #15

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6021. Min Act: -0.1700

Data Index: 8198936 (Open Web Text)

Max Activating Token Index: 535

Text #16

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.5963. Min Act: -0.1700

Data Index: 8362204 (Open Web Text)

Max Activating Token Index: 576

Text #17

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.5918. Min Act: -0.1700

Data Index: 5347303 (Open Web Text)

Max Activating Token Index: 733

Text #18

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6029. Min Act: -0.1700

Data Index: 4518759 (Open Web Text)

Max Activating Token Index: 299

Text #19

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6030. Min Act: -0.1700

Data Index: 6440350 (Open Web Text)

Max Activating Token Index: 691