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

Dataset: Open Web Text

Neuron 354 in Layer 6

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: 3.0040. Min Range: -3.0040

Max Act: 3.0040. Min Act: -0.1700

Data Index: 6250863 (Open Web Text)

Max Activating Token Index: 1020

Text #1

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.9078. Min Act: -0.1700

Data Index: 3951781 (Open Web Text)

Max Activating Token Index: 593

Text #2

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.8399. Min Act: -0.1700

Data Index: 4257759 (Open Web Text)

Max Activating Token Index: 829

Text #3

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.8081. Min Act: -0.1700

Data Index: 4950763 (Open Web Text)

Max Activating Token Index: 852

Text #4

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.7589. Min Act: -0.1700

Data Index: 3132056 (Open Web Text)

Max Activating Token Index: 777

Text #5

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.7698. Min Act: -0.1700

Data Index: 5539545 (Open Web Text)

Max Activating Token Index: 781

Text #6

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.7672. Min Act: -0.1700

Data Index: 5625742 (Open Web Text)

Max Activating Token Index: 74

Text #7

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.7541. Min Act: -0.1700

Data Index: 7143232 (Open Web Text)

Max Activating Token Index: 386

Text #8

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.7501. Min Act: -0.1700

Data Index: 4142969 (Open Web Text)

Max Activating Token Index: 160

Text #9

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.7130. Min Act: -0.1700

Data Index: 5058246 (Open Web Text)

Max Activating Token Index: 435

Text #10

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.6943. Min Act: -0.1700

Data Index: 6585962 (Open Web Text)

Max Activating Token Index: 294

Text #11

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.6772. Min Act: -0.1700

Data Index: 1165869 (Open Web Text)

Max Activating Token Index: 807

Text #12

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.6779. Min Act: -0.1700

Data Index: 3697543 (Open Web Text)

Max Activating Token Index: 692

Text #13

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.6842. Min Act: -0.1700

Data Index: 5209858 (Open Web Text)

Max Activating Token Index: 689

Text #14

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.6576. Min Act: -0.1700

Data Index: 7505973 (Open Web Text)

Max Activating Token Index: 71

Text #15

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.6432. Min Act: -0.1700

Data Index: 288222 (Open Web Text)

Max Activating Token Index: 987

Text #16

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.6577. Min Act: -0.1700

Data Index: 5028504 (Open Web Text)

Max Activating Token Index: 451

Text #17

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.6334. Min Act: -0.1700

Data Index: 7429466 (Open Web Text)

Max Activating Token Index: 29

Text #18

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.6208. Min Act: -0.1700

Data Index: 2192189 (Open Web Text)

Max Activating Token Index: 542

Text #19

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.6290. Min Act: -0.1700

Data Index: 4474393 (Open Web Text)

Max Activating Token Index: 320