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

Dataset: Open Web Text

Neuron 2173 in Layer 4

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: 4.0503. Min Range: -4.0503

Max Act: 4.0503. Min Act: -0.1700

Data Index: 3873309 (Open Web Text)

Max Activating Token Index: 374

Text #1

Max Range: 4.0503. Min Range: -4.0503

Max Act: 4.0023. Min Act: -0.1700

Data Index: 7544508 (Open Web Text)

Max Activating Token Index: 612

Text #2

Max Range: 4.0503. Min Range: -4.0503

Max Act: 4.0078. Min Act: -0.1700

Data Index: 3833229 (Open Web Text)

Max Activating Token Index: 373

Text #3

Max Range: 4.0503. Min Range: -4.0503

Max Act: 4.0202. Min Act: -0.1700

Data Index: 5644528 (Open Web Text)

Max Activating Token Index: 243

Text #4

Max Range: 4.0503. Min Range: -4.0503

Max Act: 4.0103. Min Act: -0.1700

Data Index: 8415178 (Open Web Text)

Max Activating Token Index: 622

Text #5

Max Range: 4.0503. Min Range: -4.0503

Max Act: 3.9494. Min Act: -0.1700

Data Index: 3789002 (Open Web Text)

Max Activating Token Index: 41

Text #6

Max Range: 4.0503. Min Range: -4.0503

Max Act: 4.0011. Min Act: -0.1700

Data Index: 6241084 (Open Web Text)

Max Activating Token Index: 544

Text #7

Max Range: 4.0503. Min Range: -4.0503

Max Act: 3.9917. Min Act: -0.1700

Data Index: 1598054 (Open Web Text)

Max Activating Token Index: 338

Text #8

Max Range: 4.0503. Min Range: -4.0503

Max Act: 3.9870. Min Act: -0.1700

Data Index: 2809890 (Open Web Text)

Max Activating Token Index: 133

Text #9

Max Range: 4.0503. Min Range: -4.0503

Max Act: 3.9882. Min Act: -0.1700

Data Index: 116193 (Open Web Text)

Max Activating Token Index: 378

Text #10

Max Range: 4.0503. Min Range: -4.0503

Max Act: 3.9826. Min Act: -0.1700

Data Index: 3223601 (Open Web Text)

Max Activating Token Index: 666

Text #11

Max Range: 4.0503. Min Range: -4.0503

Max Act: 3.9357. Min Act: -0.1700

Data Index: 7292582 (Open Web Text)

Max Activating Token Index: 666

Text #12

Max Range: 4.0503. Min Range: -4.0503

Max Act: 3.9330. Min Act: -0.1700

Data Index: 5661490 (Open Web Text)

Max Activating Token Index: 324

Text #13

Max Range: 4.0503. Min Range: -4.0503

Max Act: 3.9101. Min Act: -0.1700

Data Index: 3478649 (Open Web Text)

Max Activating Token Index: 861

Text #14

Max Range: 4.0503. Min Range: -4.0503

Max Act: 3.9375. Min Act: -0.1700

Data Index: 1981017 (Open Web Text)

Max Activating Token Index: 545

Text #15

Max Range: 4.0503. Min Range: -4.0503

Max Act: 3.9329. Min Act: -0.1700

Data Index: 5083963 (Open Web Text)

Max Activating Token Index: 632

Text #16

Max Range: 4.0503. Min Range: -4.0503

Max Act: 3.9284. Min Act: -0.1700

Data Index: 2862454 (Open Web Text)

Max Activating Token Index: 627

Text #17

Max Range: 4.0503. Min Range: -4.0503

Max Act: 3.9701. Min Act: -0.1700

Data Index: 4920782 (Open Web Text)

Max Activating Token Index: 593

Text #18

Max Range: 4.0503. Min Range: -4.0503

Max Act: 3.9736. Min Act: -0.1700

Data Index: 4516685 (Open Web Text)

Max Activating Token Index: 303

Text #19

Max Range: 4.0503. Min Range: -4.0503

Max Act: 3.8807. Min Act: -0.1700

Data Index: 647995 (Open Web Text)

Max Activating Token Index: 279