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

Dataset: Open Web Text

Neuron 2823 in Layer 1

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: 1.2981. Min Range: -1.2981

Max Act: 1.2981. Min Act: -0.1700

Data Index: 7918536 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2979. Min Act: -0.1700

Data Index: 7587325 (Open Web Text)

Max Activating Token Index: 83

Text #2

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2868. Min Act: -0.1700

Data Index: 4195211 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2678. Min Act: -0.1700

Data Index: 3161917 (Open Web Text)

Max Activating Token Index: 91

Text #4

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2345. Min Act: -0.1698

Data Index: 3559212 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2424. Min Act: -0.1700

Data Index: 4327584 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2377. Min Act: -0.1698

Data Index: 4207048 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2422. Min Act: -0.1700

Data Index: 6847264 (Open Web Text)

Max Activating Token Index: 114

Text #8

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2353. Min Act: -0.1700

Data Index: 7401509 (Open Web Text)

Max Activating Token Index: 834

Text #9

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2284. Min Act: -0.1700

Data Index: 6180851 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2193. Min Act: -0.1700

Data Index: 1875981 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2193. Min Act: -0.1699

Data Index: 5540921 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2193. Min Act: -0.1700

Data Index: 354596 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2193. Min Act: -0.1700

Data Index: 7117659 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2193. Min Act: -0.1700

Data Index: 3107369 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2193. Min Act: -0.1700

Data Index: 2271157 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2071. Min Act: -0.1700

Data Index: 3957786 (Open Web Text)

Max Activating Token Index: 295

Text #17

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2147. Min Act: -0.1700

Data Index: 4997910 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2198. Min Act: -0.1700

Data Index: 2034187 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2154. Min Act: -0.1699

Data Index: 1322920 (Open Web Text)

Max Activating Token Index: 5