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

Dataset: Open Web Text

Neuron 2384 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: 4.5680. Min Range: -4.5680

Max Act: 4.5680. Min Act: -0.1700

Data Index: 2060216 (Open Web Text)

Max Activating Token Index: 773

Text #1

Max Range: 4.5680. Min Range: -4.5680

Max Act: 4.5644. Min Act: -0.1700

Data Index: 5779503 (Open Web Text)

Max Activating Token Index: 476

Text #2

Max Range: 4.5680. Min Range: -4.5680

Max Act: 4.5105. Min Act: -0.1700

Data Index: 3770243 (Open Web Text)

Max Activating Token Index: 702

Text #3

Max Range: 4.5680. Min Range: -4.5680

Max Act: 4.4329. Min Act: -0.1700

Data Index: 8277546 (Open Web Text)

Max Activating Token Index: 410

Text #4

Max Range: 4.5680. Min Range: -4.5680

Max Act: 4.3503. Min Act: -0.1700

Data Index: 5141087 (Open Web Text)

Max Activating Token Index: 335

Text #5

Max Range: 4.5680. Min Range: -4.5680

Max Act: 4.3750. Min Act: -0.1700

Data Index: 2825395 (Open Web Text)

Max Activating Token Index: 603

Text #6

Max Range: 4.5680. Min Range: -4.5680

Max Act: 4.3294. Min Act: -0.1700

Data Index: 323391 (Open Web Text)

Max Activating Token Index: 535

Text #7

Max Range: 4.5680. Min Range: -4.5680

Max Act: 4.3052. Min Act: -0.1700

Data Index: 6459477 (Open Web Text)

Max Activating Token Index: 640

Text #8

Max Range: 4.5680. Min Range: -4.5680

Max Act: 4.3025. Min Act: -0.1700

Data Index: 3109748 (Open Web Text)

Max Activating Token Index: 997

Text #9

Max Range: 4.5680. Min Range: -4.5680

Max Act: 4.3070. Min Act: -0.1700

Data Index: 2293550 (Open Web Text)

Max Activating Token Index: 258

Text #10

Max Range: 4.5680. Min Range: -4.5680

Max Act: 4.2624. Min Act: -0.1700

Data Index: 2576748 (Open Web Text)

Max Activating Token Index: 479

Text #11

Max Range: 4.5680. Min Range: -4.5680

Max Act: 4.2776. Min Act: -0.1700

Data Index: 7024952 (Open Web Text)

Max Activating Token Index: 379

Text #12

Max Range: 4.5680. Min Range: -4.5680

Max Act: 4.2873. Min Act: -0.1700

Data Index: 1291731 (Open Web Text)

Max Activating Token Index: 300

Text #13

Max Range: 4.5680. Min Range: -4.5680

Max Act: 4.2835. Min Act: -0.1700

Data Index: 1536692 (Open Web Text)

Max Activating Token Index: 534

Text #14

Max Range: 4.5680. Min Range: -4.5680

Max Act: 4.2594. Min Act: -0.1700

Data Index: 2450777 (Open Web Text)

Max Activating Token Index: 983

Text #15

Max Range: 4.5680. Min Range: -4.5680

Max Act: 4.2773. Min Act: -0.1700

Data Index: 3872071 (Open Web Text)

Max Activating Token Index: 677

Text #16

Max Range: 4.5680. Min Range: -4.5680

Max Act: 4.2780. Min Act: -0.1700

Data Index: 8409799 (Open Web Text)

Max Activating Token Index: 137

Text #17

Max Range: 4.5680. Min Range: -4.5680

Max Act: 4.2431. Min Act: -0.1700

Data Index: 3193105 (Open Web Text)

Max Activating Token Index: 230

Text #18

Max Range: 4.5680. Min Range: -4.5680

Max Act: 4.2451. Min Act: -0.1700

Data Index: 4049000 (Open Web Text)

Max Activating Token Index: 595

Text #19

Max Range: 4.5680. Min Range: -4.5680

Max Act: 4.2447. Min Act: -0.1700

Data Index: 3217818 (Open Web Text)

Max Activating Token Index: 81