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

Dataset: Open Web Text

Neuron 2485 in Layer 3

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: 5.5061. Min Range: -5.5061

Max Act: 5.5061. Min Act: -0.1700

Data Index: 3220938 (Open Web Text)

Max Activating Token Index: 323

Text #1

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.3575. Min Act: -0.1700

Data Index: 3733721 (Open Web Text)

Max Activating Token Index: 200

Text #2

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.2728. Min Act: -0.1700

Data Index: 4196450 (Open Web Text)

Max Activating Token Index: 519

Text #3

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.2194. Min Act: -0.1700

Data Index: 2789816 (Open Web Text)

Max Activating Token Index: 397

Text #4

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.2221. Min Act: -0.1700

Data Index: 1098564 (Open Web Text)

Max Activating Token Index: 575

Text #5

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.2044. Min Act: -0.1700

Data Index: 1582465 (Open Web Text)

Max Activating Token Index: 780

Text #6

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1875. Min Act: -0.1700

Data Index: 6622413 (Open Web Text)

Max Activating Token Index: 803

Text #7

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1888. Min Act: -0.1700

Data Index: 7999858 (Open Web Text)

Max Activating Token Index: 69

Text #8

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1674. Min Act: -0.1700

Data Index: 7271502 (Open Web Text)

Max Activating Token Index: 176

Text #9

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1557. Min Act: -0.1700

Data Index: 2557286 (Open Web Text)

Max Activating Token Index: 495

Text #10

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1770. Min Act: -0.1700

Data Index: 7933980 (Open Web Text)

Max Activating Token Index: 907

Text #11

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1594. Min Act: -0.1700

Data Index: 7877171 (Open Web Text)

Max Activating Token Index: 380

Text #12

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1838. Min Act: -0.1700

Data Index: 1078401 (Open Web Text)

Max Activating Token Index: 1000

Text #13

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1583. Min Act: -0.1700

Data Index: 8070403 (Open Web Text)

Max Activating Token Index: 193

Text #14

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1978. Min Act: -0.1700

Data Index: 2959996 (Open Web Text)

Max Activating Token Index: 638

Text #15

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1119. Min Act: -0.1700

Data Index: 5438915 (Open Web Text)

Max Activating Token Index: 59

Text #16

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1188. Min Act: -0.1700

Data Index: 1780716 (Open Web Text)

Max Activating Token Index: 784

Text #17

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1357. Min Act: -0.1700

Data Index: 604755 (Open Web Text)

Max Activating Token Index: 548

Text #18

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1152. Min Act: -0.1700

Data Index: 7909053 (Open Web Text)

Max Activating Token Index: 484

Text #19

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1232. Min Act: -0.1700

Data Index: 3240324 (Open Web Text)

Max Activating Token Index: 126