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

Dataset: Open Web Text

Neuron 2963 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: 5.6518. Min Range: -5.6518

Max Act: 5.6518. Min Act: -0.1700

Data Index: 4895753 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.6518. Min Range: -5.6518

Max Act: 5.4534. Min Act: -0.1700

Data Index: 4554776 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.6518. Min Range: -5.6518

Max Act: 5.4216. Min Act: -0.1700

Data Index: 4980113 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 5.6518. Min Range: -5.6518

Max Act: 5.4216. Min Act: -0.1700

Data Index: 5055914 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 5.6518. Min Range: -5.6518

Max Act: 5.3817. Min Act: -0.1700

Data Index: 2030523 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 5.6518. Min Range: -5.6518

Max Act: 5.3817. Min Act: -0.1700

Data Index: 7979408 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 5.6518. Min Range: -5.6518

Max Act: 5.3817. Min Act: -0.1700

Data Index: 5405685 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 5.6518. Min Range: -5.6518

Max Act: 5.3517. Min Act: -0.1698

Data Index: 4409332 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.6518. Min Range: -5.6518

Max Act: 5.3523. Min Act: -0.1700

Data Index: 7550784 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 5.6518. Min Range: -5.6518

Max Act: 5.3523. Min Act: -0.1700

Data Index: 8169219 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 5.6518. Min Range: -5.6518

Max Act: 5.3523. Min Act: -0.1700

Data Index: 7394300 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 5.6518. Min Range: -5.6518

Max Act: 5.3523. Min Act: -0.1700

Data Index: 5974604 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 5.6518. Min Range: -5.6518

Max Act: 5.3144. Min Act: -0.1700

Data Index: 8146324 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 5.6518. Min Range: -5.6518

Max Act: 5.3214. Min Act: -0.1700

Data Index: 8587558 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.6518. Min Range: -5.6518

Max Act: 5.3192. Min Act: -0.1700

Data Index: 3511779 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 5.6518. Min Range: -5.6518

Max Act: 5.2938. Min Act: -0.1688

Data Index: 6073849 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 5.6518. Min Range: -5.6518

Max Act: 5.2702. Min Act: -0.1700

Data Index: 5017502 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 5.6518. Min Range: -5.6518

Max Act: 5.2948. Min Act: -0.1700

Data Index: 785520 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 5.6518. Min Range: -5.6518

Max Act: 5.2715. Min Act: -0.1700

Data Index: 3621024 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 5.6518. Min Range: -5.6518

Max Act: 5.2721. Min Act: -0.1700

Data Index: 436857 (Open Web Text)

Max Activating Token Index: 4