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

Dataset: Open Web Text

Neuron 2209 in Layer 2

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: 2.5561. Min Range: -2.5561

Max Act: 2.5561. Min Act: -0.1700

Data Index: 161278 (Open Web Text)

Max Activating Token Index: 510

Text #1

Max Range: 2.5561. Min Range: -2.5561

Max Act: 2.5290. Min Act: -0.1700

Data Index: 7923679 (Open Web Text)

Max Activating Token Index: 171

Text #2

Max Range: 2.5561. Min Range: -2.5561

Max Act: 2.5224. Min Act: -0.1700

Data Index: 6366077 (Open Web Text)

Max Activating Token Index: 514

Text #3

Max Range: 2.5561. Min Range: -2.5561

Max Act: 2.5040. Min Act: -0.1700

Data Index: 4234005 (Open Web Text)

Max Activating Token Index: 34

Text #4

Max Range: 2.5561. Min Range: -2.5561

Max Act: 2.5031. Min Act: -0.1700

Data Index: 2680975 (Open Web Text)

Max Activating Token Index: 507

Text #5

Max Range: 2.5561. Min Range: -2.5561

Max Act: 2.5139. Min Act: -0.1700

Data Index: 8685737 (Open Web Text)

Max Activating Token Index: 198

Text #6

Max Range: 2.5561. Min Range: -2.5561

Max Act: 2.5010. Min Act: -0.1700

Data Index: 4483881 (Open Web Text)

Max Activating Token Index: 90

Text #7

Max Range: 2.5561. Min Range: -2.5561

Max Act: 2.5053. Min Act: -0.1700

Data Index: 2407828 (Open Web Text)

Max Activating Token Index: 629

Text #8

Max Range: 2.5561. Min Range: -2.5561

Max Act: 2.4935. Min Act: -0.1700

Data Index: 2546165 (Open Web Text)

Max Activating Token Index: 175

Text #9

Max Range: 2.5561. Min Range: -2.5561

Max Act: 2.4772. Min Act: -0.1700

Data Index: 51022 (Open Web Text)

Max Activating Token Index: 285

Text #10

Max Range: 2.5561. Min Range: -2.5561

Max Act: 2.4943. Min Act: -0.1700

Data Index: 1102754 (Open Web Text)

Max Activating Token Index: 636

Text #11

Max Range: 2.5561. Min Range: -2.5561

Max Act: 2.4765. Min Act: -0.1700

Data Index: 5517183 (Open Web Text)

Max Activating Token Index: 491

Text #12

Max Range: 2.5561. Min Range: -2.5561

Max Act: 2.4765. Min Act: -0.1699

Data Index: 7874542 (Open Web Text)

Max Activating Token Index: 884

Text #13

Max Range: 2.5561. Min Range: -2.5561

Max Act: 2.4579. Min Act: -0.1700

Data Index: 2797690 (Open Web Text)

Max Activating Token Index: 401

Text #14

Max Range: 2.5561. Min Range: -2.5561

Max Act: 2.4690. Min Act: -0.1700

Data Index: 6499967 (Open Web Text)

Max Activating Token Index: 341

Text #15

Max Range: 2.5561. Min Range: -2.5561

Max Act: 2.4546. Min Act: -0.1700

Data Index: 1756032 (Open Web Text)

Max Activating Token Index: 133

Text #16

Max Range: 2.5561. Min Range: -2.5561

Max Act: 2.4601. Min Act: -0.1700

Data Index: 7299626 (Open Web Text)

Max Activating Token Index: 700

Text #17

Max Range: 2.5561. Min Range: -2.5561

Max Act: 2.4688. Min Act: -0.1700

Data Index: 3045041 (Open Web Text)

Max Activating Token Index: 680

Text #18

Max Range: 2.5561. Min Range: -2.5561

Max Act: 2.4466. Min Act: -0.1700

Data Index: 4274703 (Open Web Text)

Max Activating Token Index: 680

Text #19

Max Range: 2.5561. Min Range: -2.5561

Max Act: 2.4506. Min Act: -0.1700

Data Index: 6017196 (Open Web Text)

Max Activating Token Index: 133