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

Dataset: Open Web Text

Neuron 1263 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: 3.2789. Min Range: -3.2789

Max Act: 3.2789. Min Act: -0.1700

Data Index: 6003659 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.2789. Min Range: -3.2789

Max Act: 3.2122. Min Act: -0.1700

Data Index: 3439688 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 3.2789. Min Range: -3.2789

Max Act: 3.1925. Min Act: -0.1700

Data Index: 3306561 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.2789. Min Range: -3.2789

Max Act: 3.1935. Min Act: -0.1700

Data Index: 8725207 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 3.2789. Min Range: -3.2789

Max Act: 3.2005. Min Act: -0.1700

Data Index: 1709074 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 3.2789. Min Range: -3.2789

Max Act: 3.2067. Min Act: -0.1700

Data Index: 2425410 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.2789. Min Range: -3.2789

Max Act: 3.1781. Min Act: -0.1700

Data Index: 6458463 (Open Web Text)

Max Activating Token Index: 219

Text #7

Max Range: 3.2789. Min Range: -3.2789

Max Act: 3.1730. Min Act: -0.1700

Data Index: 4007070 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.2789. Min Range: -3.2789

Max Act: 3.1674. Min Act: -0.1700

Data Index: 7751249 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 3.2789. Min Range: -3.2789

Max Act: 3.1537. Min Act: -0.1700

Data Index: 5848030 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 3.2789. Min Range: -3.2789

Max Act: 3.1623. Min Act: -0.1700

Data Index: 5202817 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.2789. Min Range: -3.2789

Max Act: 3.1575. Min Act: -0.1700

Data Index: 7780724 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 3.2789. Min Range: -3.2789

Max Act: 3.1513. Min Act: -0.1700

Data Index: 271661 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.2789. Min Range: -3.2789

Max Act: 3.1491. Min Act: -0.1700

Data Index: 7588857 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 3.2789. Min Range: -3.2789

Max Act: 3.1475. Min Act: -0.1700

Data Index: 6770667 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.2789. Min Range: -3.2789

Max Act: 3.1579. Min Act: -0.1700

Data Index: 8814790 (Open Web Text)

Max Activating Token Index: 41

Text #16

Max Range: 3.2789. Min Range: -3.2789

Max Act: 3.1464. Min Act: -0.1700

Data Index: 7845809 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.2789. Min Range: -3.2789

Max Act: 3.1397. Min Act: -0.1700

Data Index: 6887758 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 3.2789. Min Range: -3.2789

Max Act: 3.1296. Min Act: -0.1700

Data Index: 1911551 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.2789. Min Range: -3.2789

Max Act: 3.1213. Min Act: -0.1700

Data Index: 1783023 (Open Web Text)

Max Activating Token Index: 22