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

Dataset: Open Web Text

Neuron 1098 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: 4.8662. Min Range: -4.8662

Max Act: 4.8662. Min Act: -0.1700

Data Index: 2459550 (Open Web Text)

Max Activating Token Index: 535

Text #1

Max Range: 4.8662. Min Range: -4.8662

Max Act: 4.8151. Min Act: -0.1700

Data Index: 6049609 (Open Web Text)

Max Activating Token Index: 219

Text #2

Max Range: 4.8662. Min Range: -4.8662

Max Act: 4.7843. Min Act: -0.1700

Data Index: 4831161 (Open Web Text)

Max Activating Token Index: 612

Text #3

Max Range: 4.8662. Min Range: -4.8662

Max Act: 4.7794. Min Act: -0.1700

Data Index: 2362155 (Open Web Text)

Max Activating Token Index: 454

Text #4

Max Range: 4.8662. Min Range: -4.8662

Max Act: 4.7407. Min Act: -0.1700

Data Index: 5889177 (Open Web Text)

Max Activating Token Index: 448

Text #5

Max Range: 4.8662. Min Range: -4.8662

Max Act: 4.7610. Min Act: -0.1700

Data Index: 4217361 (Open Web Text)

Max Activating Token Index: 233

Text #6

Max Range: 4.8662. Min Range: -4.8662

Max Act: 4.7262. Min Act: -0.1700

Data Index: 3081574 (Open Web Text)

Max Activating Token Index: 522

Text #7

Max Range: 4.8662. Min Range: -4.8662

Max Act: 4.7138. Min Act: -0.1700

Data Index: 4477322 (Open Web Text)

Max Activating Token Index: 484

Text #8

Max Range: 4.8662. Min Range: -4.8662

Max Act: 4.6944. Min Act: -0.1700

Data Index: 7498628 (Open Web Text)

Max Activating Token Index: 276

Text #9

Max Range: 4.8662. Min Range: -4.8662

Max Act: 4.6826. Min Act: -0.1700

Data Index: 7332374 (Open Web Text)

Max Activating Token Index: 200

Text #10

Max Range: 4.8662. Min Range: -4.8662

Max Act: 4.6668. Min Act: -0.1700

Data Index: 6363761 (Open Web Text)

Max Activating Token Index: 479

Text #11

Max Range: 4.8662. Min Range: -4.8662

Max Act: 4.6792. Min Act: -0.1700

Data Index: 4175466 (Open Web Text)

Max Activating Token Index: 545

Text #12

Max Range: 4.8662. Min Range: -4.8662

Max Act: 4.7105. Min Act: -0.1700

Data Index: 219562 (Open Web Text)

Max Activating Token Index: 541

Text #13

Max Range: 4.8662. Min Range: -4.8662

Max Act: 4.6937. Min Act: -0.1700

Data Index: 5612585 (Open Web Text)

Max Activating Token Index: 982

Text #14

Max Range: 4.8662. Min Range: -4.8662

Max Act: 4.6485. Min Act: -0.1700

Data Index: 3171766 (Open Web Text)

Max Activating Token Index: 107

Text #15

Max Range: 4.8662. Min Range: -4.8662

Max Act: 4.6671. Min Act: -0.1700

Data Index: 3591301 (Open Web Text)

Max Activating Token Index: 270

Text #16

Max Range: 4.8662. Min Range: -4.8662

Max Act: 4.6578. Min Act: -0.1700

Data Index: 4062884 (Open Web Text)

Max Activating Token Index: 120

Text #17

Max Range: 4.8662. Min Range: -4.8662

Max Act: 4.6503. Min Act: -0.1700

Data Index: 3248055 (Open Web Text)

Max Activating Token Index: 889

Text #18

Max Range: 4.8662. Min Range: -4.8662

Max Act: 4.6426. Min Act: -0.1700

Data Index: 2277195 (Open Web Text)

Max Activating Token Index: 593

Text #19

Max Range: 4.8662. Min Range: -4.8662

Max Act: 4.6788. Min Act: -0.1700

Data Index: 1008246 (Open Web Text)

Max Activating Token Index: 953