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

Dataset: Open Web Text

Neuron 1477 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: 5.4070. Min Range: -5.4070

Max Act: 5.4070. Min Act: -0.1700

Data Index: 4004286 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 5.4070. Min Range: -5.4070

Max Act: 5.3454. Min Act: -0.1700

Data Index: 7957233 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.4070. Min Range: -5.4070

Max Act: 5.2495. Min Act: -0.1700

Data Index: 1692913 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 5.4070. Min Range: -5.4070

Max Act: 5.2256. Min Act: -0.1700

Data Index: 7644747 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 5.4070. Min Range: -5.4070

Max Act: 5.2173. Min Act: -0.1700

Data Index: 108995 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 5.4070. Min Range: -5.4070

Max Act: 5.2319. Min Act: -0.1700

Data Index: 5484 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 5.4070. Min Range: -5.4070

Max Act: 5.2327. Min Act: -0.1700

Data Index: 1847573 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 5.4070. Min Range: -5.4070

Max Act: 5.2172. Min Act: -0.1700

Data Index: 3943641 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.4070. Min Range: -5.4070

Max Act: 5.2273. Min Act: -0.1700

Data Index: 4673388 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 5.4070. Min Range: -5.4070

Max Act: 5.1816. Min Act: -0.1700

Data Index: 311110 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 5.4070. Min Range: -5.4070

Max Act: 5.2110. Min Act: -0.1700

Data Index: 619090 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 5.4070. Min Range: -5.4070

Max Act: 5.1935. Min Act: -0.1700

Data Index: 7120797 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.4070. Min Range: -5.4070

Max Act: 5.2121. Min Act: -0.1700

Data Index: 3787500 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 5.4070. Min Range: -5.4070

Max Act: 5.1946. Min Act: -0.1700

Data Index: 308132 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.4070. Min Range: -5.4070

Max Act: 5.1915. Min Act: -0.1700

Data Index: 22458 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.4070. Min Range: -5.4070

Max Act: 5.2098. Min Act: -0.1700

Data Index: 4536367 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.4070. Min Range: -5.4070

Max Act: 5.1836. Min Act: -0.1700

Data Index: 3612294 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 5.4070. Min Range: -5.4070

Max Act: 5.1497. Min Act: -0.1700

Data Index: 4056539 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 5.4070. Min Range: -5.4070

Max Act: 5.1455. Min Act: -0.1700

Data Index: 3110911 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 5.4070. Min Range: -5.4070

Max Act: 5.1558. Min Act: -0.1700

Data Index: 1199416 (Open Web Text)

Max Activating Token Index: 6