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

Dataset: Open Web Text

Neuron 729 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: 3.3944. Min Range: -3.3944

Max Act: 3.3944. Min Act: -0.1700

Data Index: 3777789 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.3944. Min Range: -3.3944

Max Act: 3.3873. Min Act: -0.1700

Data Index: 5632918 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.3944. Min Range: -3.3944

Max Act: 3.2743. Min Act: -0.1700

Data Index: 1740934 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 3.3944. Min Range: -3.3944

Max Act: 3.2734. Min Act: -0.1700

Data Index: 3688363 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.3944. Min Range: -3.3944

Max Act: 3.2605. Min Act: -0.1700

Data Index: 2561882 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.3944. Min Range: -3.3944

Max Act: 3.2764. Min Act: -0.1700

Data Index: 3200948 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 3.3944. Min Range: -3.3944

Max Act: 3.2403. Min Act: -0.1700

Data Index: 6400053 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.3944. Min Range: -3.3944

Max Act: 3.2532. Min Act: -0.1700

Data Index: 978567 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.3944. Min Range: -3.3944

Max Act: 3.2341. Min Act: -0.1700

Data Index: 3186448 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.3944. Min Range: -3.3944

Max Act: 3.2245. Min Act: -0.1700

Data Index: 2504974 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.3944. Min Range: -3.3944

Max Act: 3.2061. Min Act: -0.1700

Data Index: 4330814 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 3.3944. Min Range: -3.3944

Max Act: 3.2076. Min Act: -0.1700

Data Index: 7409831 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 3.3944. Min Range: -3.3944

Max Act: 3.2164. Min Act: -0.1700

Data Index: 1478020 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 3.3944. Min Range: -3.3944

Max Act: 3.1682. Min Act: -0.1700

Data Index: 895477 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 3.3944. Min Range: -3.3944

Max Act: 3.1846. Min Act: -0.1700

Data Index: 1854653 (Open Web Text)

Max Activating Token Index: 47

Text #15

Max Range: 3.3944. Min Range: -3.3944

Max Act: 3.1739. Min Act: -0.1700

Data Index: 472809 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.3944. Min Range: -3.3944

Max Act: 3.1841. Min Act: -0.1700

Data Index: 437457 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.3944. Min Range: -3.3944

Max Act: 3.1701. Min Act: -0.1700

Data Index: 95110 (Open Web Text)

Max Activating Token Index: 18

Text #18

Max Range: 3.3944. Min Range: -3.3944

Max Act: 3.1759. Min Act: -0.1700

Data Index: 4634833 (Open Web Text)

Max Activating Token Index: 21

Text #19

Max Range: 3.3944. Min Range: -3.3944

Max Act: 3.1795. Min Act: -0.1700

Data Index: 5196380 (Open Web Text)

Max Activating Token Index: 6