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

Dataset: Open Web Text

Neuron 2794 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: 2.9700. Min Range: -2.9700

Max Act: 2.9700. Min Act: -0.1700

Data Index: 6585709 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9693. Min Act: -0.1700

Data Index: 5697833 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9564. Min Act: -0.1700

Data Index: 5080047 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9481. Min Act: -0.1700

Data Index: 4823498 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9366. Min Act: -0.1700

Data Index: 5375363 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9339. Min Act: -0.1700

Data Index: 7278816 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9114. Min Act: -0.1700

Data Index: 6824787 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9282. Min Act: -0.1700

Data Index: 1076504 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9162. Min Act: -0.1700

Data Index: 5234423 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9201. Min Act: -0.1700

Data Index: 7537979 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.8940. Min Act: -0.1700

Data Index: 3027754 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9099. Min Act: -0.1700

Data Index: 3261644 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9079. Min Act: -0.1700

Data Index: 5796459 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9132. Min Act: -0.1700

Data Index: 1510320 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.8985. Min Act: -0.1700

Data Index: 7561773 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9104. Min Act: -0.1700

Data Index: 914471 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.8999. Min Act: -0.1700

Data Index: 5370803 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.8891. Min Act: -0.1700

Data Index: 6076611 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.8816. Min Act: -0.1700

Data Index: 2590431 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.8789. Min Act: -0.1700

Data Index: 6388127 (Open Web Text)

Max Activating Token Index: 7