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

Dataset: Open Web Text

Neuron 1948 in Layer 2

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: 5.8218. Min Range: -5.8218

Max Act: 5.8218. Min Act: -0.1700

Data Index: 6059296 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.6939. Min Act: -0.1700

Data Index: 2661733 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.6939. Min Act: -0.1700

Data Index: 1362683 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.6952. Min Act: -0.1700

Data Index: 640593 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.6803. Min Act: -0.1700

Data Index: 2249681 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.6522. Min Act: -0.1700

Data Index: 8095094 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.6571. Min Act: -0.1700

Data Index: 3111225 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.6373. Min Act: -0.1700

Data Index: 3672696 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.6332. Min Act: -0.1698

Data Index: 1005235 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.6260. Min Act: -0.1700

Data Index: 529404 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.5767. Min Act: -0.1700

Data Index: 2252881 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.5495. Min Act: -0.1700

Data Index: 4504810 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.5355. Min Act: -0.1700

Data Index: 8165844 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.5355. Min Act: -0.1700

Data Index: 7109972 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.5355. Min Act: -0.1700

Data Index: 5905440 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.5355. Min Act: -0.1700

Data Index: 7552074 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.5175. Min Act: -0.1700

Data Index: 1213974 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.5310. Min Act: -0.1700

Data Index: 8830310 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.5388. Min Act: -0.1700

Data Index: 2556648 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.4665. Min Act: -0.1700

Data Index: 899349 (Open Web Text)

Max Activating Token Index: 10