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

Dataset: Open Web Text

Neuron 2217 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: 2.2753. Min Range: -2.2753

Max Act: 2.2753. Min Act: -0.1700

Data Index: 2159215 (Open Web Text)

Max Activating Token Index: 41

Text #1

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.2234. Min Act: -0.1700

Data Index: 8623468 (Open Web Text)

Max Activating Token Index: 384

Text #2

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.2258. Min Act: -0.1700

Data Index: 3470075 (Open Web Text)

Max Activating Token Index: 1015

Text #3

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.2109. Min Act: -0.1700

Data Index: 6591130 (Open Web Text)

Max Activating Token Index: 569

Text #4

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.1976. Min Act: -0.1700

Data Index: 4713424 (Open Web Text)

Max Activating Token Index: 345

Text #5

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.1787. Min Act: -0.1700

Data Index: 752600 (Open Web Text)

Max Activating Token Index: 1022

Text #6

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.1835. Min Act: -0.1700

Data Index: 7955990 (Open Web Text)

Max Activating Token Index: 679

Text #7

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.1725. Min Act: -0.1700

Data Index: 1517398 (Open Web Text)

Max Activating Token Index: 495

Text #8

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.1557. Min Act: -0.1700

Data Index: 577938 (Open Web Text)

Max Activating Token Index: 662

Text #9

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.1640. Min Act: -0.1700

Data Index: 1811790 (Open Web Text)

Max Activating Token Index: 147

Text #10

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.1666. Min Act: -0.1700

Data Index: 2040759 (Open Web Text)

Max Activating Token Index: 129

Text #11

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.1644. Min Act: -0.1700

Data Index: 5489133 (Open Web Text)

Max Activating Token Index: 512

Text #12

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.1644. Min Act: -0.1700

Data Index: 138926 (Open Web Text)

Max Activating Token Index: 61

Text #13

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.1428. Min Act: -0.1700

Data Index: 6851699 (Open Web Text)

Max Activating Token Index: 704

Text #14

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.1426. Min Act: -0.1700

Data Index: 5690203 (Open Web Text)

Max Activating Token Index: 365

Text #15

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.1578. Min Act: -0.1700

Data Index: 4860823 (Open Web Text)

Max Activating Token Index: 67

Text #16

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.1456. Min Act: -0.1700

Data Index: 4751539 (Open Web Text)

Max Activating Token Index: 204

Text #17

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.1367. Min Act: -0.1700

Data Index: 385499 (Open Web Text)

Max Activating Token Index: 656

Text #18

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.1395. Min Act: -0.1700

Data Index: 1385323 (Open Web Text)

Max Activating Token Index: 1015

Text #19

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.1440. Min Act: -0.1700

Data Index: 2084465 (Open Web Text)

Max Activating Token Index: 700