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

Dataset: Open Web Text

Neuron 1446 in Layer 6

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: 4.4986. Min Range: -4.4986

Max Act: 4.4986. Min Act: -0.1700

Data Index: 3650333 (Open Web Text)

Max Activating Token Index: 204

Text #1

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.4882. Min Act: -0.1700

Data Index: 1276670 (Open Web Text)

Max Activating Token Index: 268

Text #2

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.4447. Min Act: -0.1700

Data Index: 5889836 (Open Web Text)

Max Activating Token Index: 190

Text #3

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.4188. Min Act: -0.1700

Data Index: 1121607 (Open Web Text)

Max Activating Token Index: 914

Text #4

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.4087. Min Act: -0.1700

Data Index: 856534 (Open Web Text)

Max Activating Token Index: 431

Text #5

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3849. Min Act: -0.1700

Data Index: 8502453 (Open Web Text)

Max Activating Token Index: 793

Text #6

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3555. Min Act: -0.1700

Data Index: 1553735 (Open Web Text)

Max Activating Token Index: 158

Text #7

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3839. Min Act: -0.1700

Data Index: 2031487 (Open Web Text)

Max Activating Token Index: 501

Text #8

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3799. Min Act: -0.1700

Data Index: 5935725 (Open Web Text)

Max Activating Token Index: 800

Text #9

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3751. Min Act: -0.1700

Data Index: 3518111 (Open Web Text)

Max Activating Token Index: 845

Text #10

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3387. Min Act: -0.1700

Data Index: 1644512 (Open Web Text)

Max Activating Token Index: 586

Text #11

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3275. Min Act: -0.1700

Data Index: 855080 (Open Web Text)

Max Activating Token Index: 740

Text #12

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3365. Min Act: -0.1700

Data Index: 5918505 (Open Web Text)

Max Activating Token Index: 340

Text #13

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3275. Min Act: -0.1700

Data Index: 7688649 (Open Web Text)

Max Activating Token Index: 124

Text #14

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3241. Min Act: -0.1700

Data Index: 5068508 (Open Web Text)

Max Activating Token Index: 352

Text #15

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3288. Min Act: -0.1700

Data Index: 4485265 (Open Web Text)

Max Activating Token Index: 793

Text #16

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3207. Min Act: -0.1700

Data Index: 4096889 (Open Web Text)

Max Activating Token Index: 103

Text #17

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3322. Min Act: -0.1700

Data Index: 7243302 (Open Web Text)

Max Activating Token Index: 342

Text #18

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3353. Min Act: -0.1700

Data Index: 6830164 (Open Web Text)

Max Activating Token Index: 215

Text #19

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3304. Min Act: -0.1700

Data Index: 6299206 (Open Web Text)

Max Activating Token Index: 179