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

Dataset: Open Web Text

Neuron 1832 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: 4.5071. Min Range: -4.5071

Max Act: 4.5071. Min Act: -0.1700

Data Index: 3026613 (Open Web Text)

Max Activating Token Index: 31

Text #1

Max Range: 4.5071. Min Range: -4.5071

Max Act: 4.4412. Min Act: -0.1700

Data Index: 3291969 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.5071. Min Range: -4.5071

Max Act: 4.4109. Min Act: -0.1700

Data Index: 6161842 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 4.5071. Min Range: -4.5071

Max Act: 4.3807. Min Act: -0.1700

Data Index: 424406 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 4.5071. Min Range: -4.5071

Max Act: 4.3636. Min Act: -0.1700

Data Index: 3322540 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.5071. Min Range: -4.5071

Max Act: 4.3598. Min Act: -0.1700

Data Index: 1660145 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.5071. Min Range: -4.5071

Max Act: 4.3726. Min Act: -0.1700

Data Index: 155329 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 4.5071. Min Range: -4.5071

Max Act: 4.3659. Min Act: -0.1700

Data Index: 8329853 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 4.5071. Min Range: -4.5071

Max Act: 4.3298. Min Act: -0.1700

Data Index: 1310278 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.5071. Min Range: -4.5071

Max Act: 4.3272. Min Act: -0.1700

Data Index: 3002871 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.5071. Min Range: -4.5071

Max Act: 4.3500. Min Act: -0.1700

Data Index: 3270174 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.5071. Min Range: -4.5071

Max Act: 4.3589. Min Act: -0.1700

Data Index: 5388719 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 4.5071. Min Range: -4.5071

Max Act: 4.3242. Min Act: -0.1700

Data Index: 953586 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.5071. Min Range: -4.5071

Max Act: 4.3162. Min Act: -0.1700

Data Index: 1338496 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.5071. Min Range: -4.5071

Max Act: 4.3267. Min Act: -0.1700

Data Index: 233705 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 4.5071. Min Range: -4.5071

Max Act: 4.3135. Min Act: -0.1700

Data Index: 1806612 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.5071. Min Range: -4.5071

Max Act: 4.3080. Min Act: -0.1700

Data Index: 1922616 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.5071. Min Range: -4.5071

Max Act: 4.3224. Min Act: -0.1700

Data Index: 2923348 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.5071. Min Range: -4.5071

Max Act: 4.3164. Min Act: -0.1700

Data Index: 4658530 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.5071. Min Range: -4.5071

Max Act: 4.3056. Min Act: -0.1700

Data Index: 5462585 (Open Web Text)

Max Activating Token Index: 3