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

Dataset: Open Web Text

Neuron 539 in Layer 1

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: 3.9534. Min Range: -3.9534

Max Act: 3.9534. Min Act: -0.1700

Data Index: 7887984 (Open Web Text)

Max Activating Token Index: 512

Text #1

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.9138. Min Act: -0.1700

Data Index: 5889265 (Open Web Text)

Max Activating Token Index: 466

Text #2

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8762. Min Act: -0.1700

Data Index: 3623953 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8606. Min Act: -0.1700

Data Index: 241166 (Open Web Text)

Max Activating Token Index: 417

Text #4

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8246. Min Act: -0.1700

Data Index: 2492235 (Open Web Text)

Max Activating Token Index: 550

Text #5

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8350. Min Act: -0.1700

Data Index: 6472984 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8181. Min Act: -0.1700

Data Index: 4855314 (Open Web Text)

Max Activating Token Index: 198

Text #7

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8061. Min Act: -0.1700

Data Index: 6632277 (Open Web Text)

Max Activating Token Index: 737

Text #8

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.7830. Min Act: -0.1700

Data Index: 3665137 (Open Web Text)

Max Activating Token Index: 455

Text #9

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.7742. Min Act: -0.1700

Data Index: 3099831 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8108. Min Act: -0.1700

Data Index: 2193743 (Open Web Text)

Max Activating Token Index: 509

Text #11

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.7746. Min Act: -0.1700

Data Index: 1303954 (Open Web Text)

Max Activating Token Index: 493

Text #12

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.7766. Min Act: -0.1700

Data Index: 4692733 (Open Web Text)

Max Activating Token Index: 572

Text #13

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.7925. Min Act: -0.1700

Data Index: 4319221 (Open Web Text)

Max Activating Token Index: 191

Text #14

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8032. Min Act: -0.1700

Data Index: 8190201 (Open Web Text)

Max Activating Token Index: 68

Text #15

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.7917. Min Act: -0.1700

Data Index: 7976617 (Open Web Text)

Max Activating Token Index: 802

Text #16

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.7980. Min Act: -0.1700

Data Index: 1903216 (Open Web Text)

Max Activating Token Index: 367

Text #17

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.8066. Min Act: -0.1700

Data Index: 5440138 (Open Web Text)

Max Activating Token Index: 838

Text #18

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.7506. Min Act: -0.1700

Data Index: 1011144 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.9534. Min Range: -3.9534

Max Act: 3.7918. Min Act: -0.1700

Data Index: 5581199 (Open Web Text)

Max Activating Token Index: 579