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

Dataset: Open Web Text

Neuron 1563 in Layer 0

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: 2.0542. Min Range: -2.0542

Max Act: 2.0439. Min Act: -0.1700

Data Index: 1007937 (Open Web Text)

Max Activating Token Index: 697

Text #1

Max Range: 2.0542. Min Range: -2.0542

Max Act: 2.0542. Min Act: -0.1700

Data Index: 6811553 (Open Web Text)

Max Activating Token Index: 676

Text #2

Max Range: 2.0542. Min Range: -2.0542

Max Act: 2.0052. Min Act: -0.1700

Data Index: 402234 (Open Web Text)

Max Activating Token Index: 684

Text #3

Max Range: 2.0542. Min Range: -2.0542

Max Act: 1.9761. Min Act: -0.1700

Data Index: 8267551 (Open Web Text)

Max Activating Token Index: 684

Text #4

Max Range: 2.0542. Min Range: -2.0542

Max Act: 1.9890. Min Act: -0.1700

Data Index: 3366440 (Open Web Text)

Max Activating Token Index: 662

Text #5

Max Range: 2.0542. Min Range: -2.0542

Max Act: 1.9833. Min Act: -0.1700

Data Index: 3724017 (Open Web Text)

Max Activating Token Index: 697

Text #6

Max Range: 2.0542. Min Range: -2.0542

Max Act: 1.9932. Min Act: -0.1700

Data Index: 1547371 (Open Web Text)

Max Activating Token Index: 690

Text #7

Max Range: 2.0542. Min Range: -2.0542

Max Act: 1.9806. Min Act: -0.1700

Data Index: 2549425 (Open Web Text)

Max Activating Token Index: 669

Text #8

Max Range: 2.0542. Min Range: -2.0542

Max Act: 1.9784. Min Act: -0.1700

Data Index: 2516404 (Open Web Text)

Max Activating Token Index: 689

Text #9

Max Range: 2.0542. Min Range: -2.0542

Max Act: 1.9674. Min Act: -0.1700

Data Index: 795761 (Open Web Text)

Max Activating Token Index: 684

Text #10

Max Range: 2.0542. Min Range: -2.0542

Max Act: 1.9667. Min Act: -0.1700

Data Index: 490724 (Open Web Text)

Max Activating Token Index: 676

Text #11

Max Range: 2.0542. Min Range: -2.0542

Max Act: 1.9644. Min Act: -0.1700

Data Index: 8026132 (Open Web Text)

Max Activating Token Index: 695

Text #12

Max Range: 2.0542. Min Range: -2.0542

Max Act: 1.9569. Min Act: -0.1700

Data Index: 2485096 (Open Web Text)

Max Activating Token Index: 683

Text #13

Max Range: 2.0542. Min Range: -2.0542

Max Act: 1.9699. Min Act: -0.1700

Data Index: 5934388 (Open Web Text)

Max Activating Token Index: 646

Text #14

Max Range: 2.0542. Min Range: -2.0542

Max Act: 1.9424. Min Act: -0.1700

Data Index: 2847706 (Open Web Text)

Max Activating Token Index: 669

Text #15

Max Range: 2.0542. Min Range: -2.0542

Max Act: 1.9544. Min Act: -0.1700

Data Index: 4719845 (Open Web Text)

Max Activating Token Index: 681

Text #16

Max Range: 2.0542. Min Range: -2.0542

Max Act: 1.9490. Min Act: -0.1700

Data Index: 2824371 (Open Web Text)

Max Activating Token Index: 678

Text #17

Max Range: 2.0542. Min Range: -2.0542

Max Act: 1.9550. Min Act: -0.1700

Data Index: 7558376 (Open Web Text)

Max Activating Token Index: 666

Text #18

Max Range: 2.0542. Min Range: -2.0542

Max Act: 1.9542. Min Act: -0.1700

Data Index: 2659897 (Open Web Text)

Max Activating Token Index: 697

Text #19

Max Range: 2.0542. Min Range: -2.0542

Max Act: 1.9456. Min Act: -0.1700

Data Index: 1452939 (Open Web Text)

Max Activating Token Index: 666