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

Dataset: Open Web Text

Neuron 952 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: 4.3041. Min Range: -4.3041

Max Act: 4.3041. Min Act: -0.1700

Data Index: 6113227 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.3041. Min Range: -4.3041

Max Act: 4.2227. Min Act: -0.1700

Data Index: 2923789 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.3041. Min Range: -4.3041

Max Act: 4.1766. Min Act: -0.1700

Data Index: 3177143 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.3041. Min Range: -4.3041

Max Act: 4.1224. Min Act: -0.1700

Data Index: 1403402 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.3041. Min Range: -4.3041

Max Act: 4.1316. Min Act: -0.1700

Data Index: 391580 (Open Web Text)

Max Activating Token Index: 951

Text #5

Max Range: 4.3041. Min Range: -4.3041

Max Act: 4.0969. Min Act: -0.1700

Data Index: 767497 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.3041. Min Range: -4.3041

Max Act: 4.0998. Min Act: -0.1700

Data Index: 5390211 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.3041. Min Range: -4.3041

Max Act: 4.1206. Min Act: -0.1700

Data Index: 1532903 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.3041. Min Range: -4.3041

Max Act: 4.1092. Min Act: -0.1700

Data Index: 8610367 (Open Web Text)

Max Activating Token Index: 938

Text #9

Max Range: 4.3041. Min Range: -4.3041

Max Act: 4.0990. Min Act: -0.1700

Data Index: 6997771 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.3041. Min Range: -4.3041

Max Act: 4.0598. Min Act: -0.1700

Data Index: 5200023 (Open Web Text)

Max Activating Token Index: 975

Text #11

Max Range: 4.3041. Min Range: -4.3041

Max Act: 4.0860. Min Act: -0.1700

Data Index: 1112857 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.3041. Min Range: -4.3041

Max Act: 4.0736. Min Act: -0.1700

Data Index: 5160600 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.3041. Min Range: -4.3041

Max Act: 4.0710. Min Act: -0.1700

Data Index: 4202115 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.3041. Min Range: -4.3041

Max Act: 4.0807. Min Act: -0.1700

Data Index: 5558024 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 4.3041. Min Range: -4.3041

Max Act: 4.0565. Min Act: -0.1700

Data Index: 1728452 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 4.3041. Min Range: -4.3041

Max Act: 4.0800. Min Act: -0.1700

Data Index: 1744127 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 4.3041. Min Range: -4.3041

Max Act: 4.0659. Min Act: -0.1700

Data Index: 2164812 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.3041. Min Range: -4.3041

Max Act: 4.0736. Min Act: -0.1700

Data Index: 6657088 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.3041. Min Range: -4.3041

Max Act: 4.0645. Min Act: -0.1700

Data Index: 2605331 (Open Web Text)

Max Activating Token Index: 897