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

Dataset: Open Web Text

Neuron 717 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: 4.8765. Min Range: -4.8765

Max Act: 4.8761. Min Act: -0.1700

Data Index: 4152137 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8590. Min Act: -0.1700

Data Index: 7671481 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8590. Min Act: -0.1700

Data Index: 656572 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8765. Min Act: -0.1700

Data Index: 3085826 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8582. Min Act: -0.1700

Data Index: 5072900 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8448. Min Act: -0.1700

Data Index: 1367565 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8189. Min Act: -0.1700

Data Index: 5959350 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8171. Min Act: -0.1700

Data Index: 6169101 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8195. Min Act: -0.1700

Data Index: 7164439 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8157. Min Act: -0.1700

Data Index: 7577265 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8094. Min Act: -0.1700

Data Index: 8365687 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8248. Min Act: -0.1700

Data Index: 905592 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8119. Min Act: -0.1700

Data Index: 5519854 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.7932. Min Act: -0.1700

Data Index: 1048282 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.7940. Min Act: -0.1700

Data Index: 5554188 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8044. Min Act: -0.1700

Data Index: 5373487 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.7955. Min Act: -0.1700

Data Index: 3305892 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.7918. Min Act: -0.1700

Data Index: 4626106 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8139. Min Act: -0.1700

Data Index: 2578359 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.7929. Min Act: -0.1700

Data Index: 663094 (Open Web Text)

Max Activating Token Index: 7