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

Dataset: Open Web Text

Neuron 588 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: 3.0529. Min Range: -3.0529

Max Act: 3.0476. Min Act: -0.1700

Data Index: 5438676 (Open Web Text)

Max Activating Token Index: 454

Text #1

Max Range: 3.0529. Min Range: -3.0529

Max Act: 3.0529. Min Act: -0.1700

Data Index: 3346780 (Open Web Text)

Max Activating Token Index: 71

Text #2

Max Range: 3.0529. Min Range: -3.0529

Max Act: 3.0167. Min Act: -0.1700

Data Index: 1735621 (Open Web Text)

Max Activating Token Index: 43

Text #3

Max Range: 3.0529. Min Range: -3.0529

Max Act: 3.0387. Min Act: -0.1700

Data Index: 6591199 (Open Web Text)

Max Activating Token Index: 509

Text #4

Max Range: 3.0529. Min Range: -3.0529

Max Act: 3.0092. Min Act: -0.1700

Data Index: 2847441 (Open Web Text)

Max Activating Token Index: 557

Text #5

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9864. Min Act: -0.1700

Data Index: 62928 (Open Web Text)

Max Activating Token Index: 582

Text #6

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9687. Min Act: -0.1700

Data Index: 21476 (Open Web Text)

Max Activating Token Index: 22

Text #7

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9482. Min Act: -0.1700

Data Index: 2123225 (Open Web Text)

Max Activating Token Index: 909

Text #8

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9637. Min Act: -0.1700

Data Index: 3143196 (Open Web Text)

Max Activating Token Index: 140

Text #9

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9522. Min Act: -0.1700

Data Index: 5391495 (Open Web Text)

Max Activating Token Index: 31

Text #10

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9241. Min Act: -0.1700

Data Index: 8818600 (Open Web Text)

Max Activating Token Index: 738

Text #11

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9462. Min Act: -0.1700

Data Index: 2309952 (Open Web Text)

Max Activating Token Index: 753

Text #12

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9533. Min Act: -0.1700

Data Index: 8362089 (Open Web Text)

Max Activating Token Index: 181

Text #13

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9341. Min Act: -0.1700

Data Index: 674571 (Open Web Text)

Max Activating Token Index: 495

Text #14

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9133. Min Act: -0.1700

Data Index: 1111044 (Open Web Text)

Max Activating Token Index: 749

Text #15

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9225. Min Act: -0.1700

Data Index: 5055608 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.8942. Min Act: -0.1700

Data Index: 5162793 (Open Web Text)

Max Activating Token Index: 387

Text #17

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9248. Min Act: -0.1700

Data Index: 7500150 (Open Web Text)

Max Activating Token Index: 489

Text #18

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.8725. Min Act: -0.1700

Data Index: 6944998 (Open Web Text)

Max Activating Token Index: 486

Text #19

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9280. Min Act: -0.1700

Data Index: 3979698 (Open Web Text)

Max Activating Token Index: 702