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

Dataset: Open Web Text

Neuron 2043 in Layer 5

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: 4.0342. Min Range: -4.0342

Max Act: 4.0342. Min Act: -0.1700

Data Index: 81495 (Open Web Text)

Max Activating Token Index: 241

Text #1

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.8484. Min Act: -0.1700

Data Index: 8063204 (Open Web Text)

Max Activating Token Index: 666

Text #2

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.8498. Min Act: -0.1700

Data Index: 2939984 (Open Web Text)

Max Activating Token Index: 172

Text #3

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.8989. Min Act: -0.1700

Data Index: 3265348 (Open Web Text)

Max Activating Token Index: 550

Text #4

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.7676. Min Act: -0.1700

Data Index: 1976739 (Open Web Text)

Max Activating Token Index: 129

Text #5

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.7599. Min Act: -0.1700

Data Index: 8660043 (Open Web Text)

Max Activating Token Index: 959

Text #6

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.7472. Min Act: -0.1700

Data Index: 1657163 (Open Web Text)

Max Activating Token Index: 956

Text #7

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.7044. Min Act: -0.1700

Data Index: 660595 (Open Web Text)

Max Activating Token Index: 703

Text #8

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.7421. Min Act: -0.1700

Data Index: 5281895 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.7180. Min Act: -0.1700

Data Index: 3940181 (Open Web Text)

Max Activating Token Index: 561

Text #10

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.7059. Min Act: -0.1700

Data Index: 8318459 (Open Web Text)

Max Activating Token Index: 69

Text #11

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.7219. Min Act: -0.1700

Data Index: 6398080 (Open Web Text)

Max Activating Token Index: 370

Text #12

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.6769. Min Act: -0.1700

Data Index: 6166720 (Open Web Text)

Max Activating Token Index: 186

Text #13

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.6858. Min Act: -0.1700

Data Index: 5565385 (Open Web Text)

Max Activating Token Index: 393

Text #14

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.6834. Min Act: -0.1700

Data Index: 6335835 (Open Web Text)

Max Activating Token Index: 792

Text #15

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.6793. Min Act: -0.1700

Data Index: 2047897 (Open Web Text)

Max Activating Token Index: 910

Text #16

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.6690. Min Act: -0.1700

Data Index: 3328769 (Open Web Text)

Max Activating Token Index: 274

Text #17

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.6420. Min Act: -0.1700

Data Index: 2428262 (Open Web Text)

Max Activating Token Index: 788

Text #18

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.6664. Min Act: -0.1700

Data Index: 6953288 (Open Web Text)

Max Activating Token Index: 85

Text #19

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.6609. Min Act: -0.1700

Data Index: 209820 (Open Web Text)

Max Activating Token Index: 561