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

Dataset: Open Web Text

Neuron 1508 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: 3.5417. Min Range: -3.5417

Max Act: 3.5417. Min Act: -0.1700

Data Index: 3190322 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.5062. Min Act: -0.1700

Data Index: 7439258 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.4672. Min Act: -0.1700

Data Index: 7150162 (Open Web Text)

Max Activating Token Index: 15

Text #3

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.4898. Min Act: -0.1700

Data Index: 3221 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.4767. Min Act: -0.1700

Data Index: 8226620 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.4281. Min Act: -0.1700

Data Index: 6509243 (Open Web Text)

Max Activating Token Index: 901

Text #6

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3805. Min Act: -0.1700

Data Index: 6197531 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3973. Min Act: -0.1700

Data Index: 5130886 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3849. Min Act: -0.1700

Data Index: 4019298 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3793. Min Act: -0.1700

Data Index: 7901444 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3660. Min Act: -0.1700

Data Index: 7906400 (Open Web Text)

Max Activating Token Index: 1021

Text #11

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3809. Min Act: -0.1700

Data Index: 2111974 (Open Web Text)

Max Activating Token Index: 682

Text #12

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3684. Min Act: -0.1700

Data Index: 2469046 (Open Web Text)

Max Activating Token Index: 15

Text #13

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3597. Min Act: -0.1700

Data Index: 5961706 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3499. Min Act: -0.1700

Data Index: 7102797 (Open Web Text)

Max Activating Token Index: 33

Text #15

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3652. Min Act: -0.1700

Data Index: 4756210 (Open Web Text)

Max Activating Token Index: 15

Text #16

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3398. Min Act: -0.1700

Data Index: 7292315 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3627. Min Act: -0.1700

Data Index: 2936342 (Open Web Text)

Max Activating Token Index: 717

Text #18

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3412. Min Act: -0.1700

Data Index: 266871 (Open Web Text)

Max Activating Token Index: 961

Text #19

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3536. Min Act: -0.1700

Data Index: 3154367 (Open Web Text)

Max Activating Token Index: 32