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

Dataset: Open Web Text

Neuron 2540 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: 3.3445. Min Range: -3.3445

Max Act: 3.3445. Min Act: -0.1700

Data Index: 3427392 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.3445. Min Range: -3.3445

Max Act: 3.3361. Min Act: -0.1700

Data Index: 6983890 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.3445. Min Range: -3.3445

Max Act: 3.3328. Min Act: -0.1700

Data Index: 8784491 (Open Web Text)

Max Activating Token Index: 60

Text #3

Max Range: 3.3445. Min Range: -3.3445

Max Act: 3.3296. Min Act: -0.1700

Data Index: 6853546 (Open Web Text)

Max Activating Token Index: 73

Text #4

Max Range: 3.3445. Min Range: -3.3445

Max Act: 3.2516. Min Act: -0.1700

Data Index: 8688377 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.3445. Min Range: -3.3445

Max Act: 3.2671. Min Act: -0.1700

Data Index: 6930293 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.3445. Min Range: -3.3445

Max Act: 3.2784. Min Act: -0.1700

Data Index: 3477537 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.3445. Min Range: -3.3445

Max Act: 3.2516. Min Act: -0.1700

Data Index: 6519203 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.3445. Min Range: -3.3445

Max Act: 3.2484. Min Act: -0.1700

Data Index: 6049516 (Open Web Text)

Max Activating Token Index: 618

Text #9

Max Range: 3.3445. Min Range: -3.3445

Max Act: 3.2561. Min Act: -0.1700

Data Index: 1166204 (Open Web Text)

Max Activating Token Index: 1002

Text #10

Max Range: 3.3445. Min Range: -3.3445

Max Act: 3.2586. Min Act: -0.1700

Data Index: 5727610 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.3445. Min Range: -3.3445

Max Act: 3.2530. Min Act: -0.1700

Data Index: 8773959 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.3445. Min Range: -3.3445

Max Act: 3.2685. Min Act: -0.1700

Data Index: 3759067 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.3445. Min Range: -3.3445

Max Act: 3.2203. Min Act: -0.1700

Data Index: 6802123 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.3445. Min Range: -3.3445

Max Act: 3.2373. Min Act: -0.1700

Data Index: 3410004 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.3445. Min Range: -3.3445

Max Act: 3.2227. Min Act: -0.1700

Data Index: 1449430 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.3445. Min Range: -3.3445

Max Act: 3.2344. Min Act: -0.1700

Data Index: 5678243 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.3445. Min Range: -3.3445

Max Act: 3.2300. Min Act: -0.1700

Data Index: 163741 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.3445. Min Range: -3.3445

Max Act: 3.2463. Min Act: -0.1700

Data Index: 3507976 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.3445. Min Range: -3.3445

Max Act: 3.2408. Min Act: -0.1700

Data Index: 3508960 (Open Web Text)

Max Activating Token Index: 3