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

Dataset: Open Web Text

Neuron 1915 in Layer 3

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: 4.6531. Min Range: -4.6531

Max Act: 4.5506. Min Act: -0.1700

Data Index: 6707123 (Open Web Text)

Max Activating Token Index: 582

Text #1

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.6531. Min Act: -0.1700

Data Index: 6724333 (Open Web Text)

Max Activating Token Index: 608

Text #2

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.4052. Min Act: -0.1700

Data Index: 3397224 (Open Web Text)

Max Activating Token Index: 501

Text #3

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.5170. Min Act: -0.1700

Data Index: 6403427 (Open Web Text)

Max Activating Token Index: 53

Text #4

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.5530. Min Act: -0.1700

Data Index: 8185810 (Open Web Text)

Max Activating Token Index: 366

Text #5

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.5306. Min Act: -0.1700

Data Index: 6771075 (Open Web Text)

Max Activating Token Index: 173

Text #6

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.5531. Min Act: -0.1700

Data Index: 1708611 (Open Web Text)

Max Activating Token Index: 62

Text #7

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.4506. Min Act: -0.1700

Data Index: 7337967 (Open Web Text)

Max Activating Token Index: 521

Text #8

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.5084. Min Act: -0.1700

Data Index: 1700691 (Open Web Text)

Max Activating Token Index: 23

Text #9

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.5053. Min Act: -0.1700

Data Index: 5302755 (Open Web Text)

Max Activating Token Index: 575

Text #10

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.4828. Min Act: -0.1700

Data Index: 8539548 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.5031. Min Act: -0.1700

Data Index: 7551464 (Open Web Text)

Max Activating Token Index: 529

Text #12

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.5374. Min Act: -0.1700

Data Index: 4012640 (Open Web Text)

Max Activating Token Index: 662

Text #13

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.4730. Min Act: -0.1700

Data Index: 3365699 (Open Web Text)

Max Activating Token Index: 791

Text #14

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.5346. Min Act: -0.1700

Data Index: 3011515 (Open Web Text)

Max Activating Token Index: 652

Text #15

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.5007. Min Act: -0.1700

Data Index: 3788748 (Open Web Text)

Max Activating Token Index: 67

Text #16

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.4406. Min Act: -0.1700

Data Index: 1691046 (Open Web Text)

Max Activating Token Index: 59

Text #17

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.4782. Min Act: -0.1700

Data Index: 5313912 (Open Web Text)

Max Activating Token Index: 628

Text #18

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.4772. Min Act: -0.1700

Data Index: 3657128 (Open Web Text)

Max Activating Token Index: 464

Text #19

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.4773. Min Act: -0.1700

Data Index: 501945 (Open Web Text)

Max Activating Token Index: 286