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

Dataset: Open Web Text

Neuron 18 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: 4.6566. Min Range: -4.6566

Max Act: 4.6381. Min Act: -0.1700

Data Index: 6258129 (Open Web Text)

Max Activating Token Index: 528

Text #1

Max Range: 4.6566. Min Range: -4.6566

Max Act: 4.6566. Min Act: -0.1700

Data Index: 3449009 (Open Web Text)

Max Activating Token Index: 851

Text #2

Max Range: 4.6566. Min Range: -4.6566

Max Act: 4.4852. Min Act: -0.1700

Data Index: 5974619 (Open Web Text)

Max Activating Token Index: 275

Text #3

Max Range: 4.6566. Min Range: -4.6566

Max Act: 4.3871. Min Act: -0.1700

Data Index: 3555443 (Open Web Text)

Max Activating Token Index: 74

Text #4

Max Range: 4.6566. Min Range: -4.6566

Max Act: 4.4067. Min Act: -0.1700

Data Index: 7584181 (Open Web Text)

Max Activating Token Index: 790

Text #5

Max Range: 4.6566. Min Range: -4.6566

Max Act: 4.3543. Min Act: -0.1700

Data Index: 8489812 (Open Web Text)

Max Activating Token Index: 65

Text #6

Max Range: 4.6566. Min Range: -4.6566

Max Act: 4.3642. Min Act: -0.1700

Data Index: 5736226 (Open Web Text)

Max Activating Token Index: 74

Text #7

Max Range: 4.6566. Min Range: -4.6566

Max Act: 4.3204. Min Act: -0.1700

Data Index: 1518342 (Open Web Text)

Max Activating Token Index: 636

Text #8

Max Range: 4.6566. Min Range: -4.6566

Max Act: 4.3410. Min Act: -0.1700

Data Index: 7330174 (Open Web Text)

Max Activating Token Index: 466

Text #9

Max Range: 4.6566. Min Range: -4.6566

Max Act: 4.3200. Min Act: -0.1700

Data Index: 8078071 (Open Web Text)

Max Activating Token Index: 582

Text #10

Max Range: 4.6566. Min Range: -4.6566

Max Act: 4.2881. Min Act: -0.1700

Data Index: 3883284 (Open Web Text)

Max Activating Token Index: 629

Text #11

Max Range: 4.6566. Min Range: -4.6566

Max Act: 4.2787. Min Act: -0.1700

Data Index: 1204395 (Open Web Text)

Max Activating Token Index: 248

Text #12

Max Range: 4.6566. Min Range: -4.6566

Max Act: 4.3333. Min Act: -0.1700

Data Index: 7297831 (Open Web Text)

Max Activating Token Index: 462

Text #13

Max Range: 4.6566. Min Range: -4.6566

Max Act: 4.2708. Min Act: -0.1700

Data Index: 8313250 (Open Web Text)

Max Activating Token Index: 526

Text #14

Max Range: 4.6566. Min Range: -4.6566

Max Act: 4.2873. Min Act: -0.1700

Data Index: 5225904 (Open Web Text)

Max Activating Token Index: 94

Text #15

Max Range: 4.6566. Min Range: -4.6566

Max Act: 4.2517. Min Act: -0.1700

Data Index: 5362977 (Open Web Text)

Max Activating Token Index: 555

Text #16

Max Range: 4.6566. Min Range: -4.6566

Max Act: 4.2039. Min Act: -0.1700

Data Index: 5604374 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.6566. Min Range: -4.6566

Max Act: 4.2318. Min Act: -0.1700

Data Index: 2070532 (Open Web Text)

Max Activating Token Index: 527

Text #18

Max Range: 4.6566. Min Range: -4.6566

Max Act: 4.2039. Min Act: -0.1700

Data Index: 2256755 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.6566. Min Range: -4.6566

Max Act: 4.2079. Min Act: -0.1700

Data Index: 8182196 (Open Web Text)

Max Activating Token Index: 3