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

Dataset: Open Web Text

Neuron 2889 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: 1.6802. Min Range: -1.6802

Max Act: 1.6759. Min Act: -0.1700

Data Index: 6449269 (Open Web Text)

Max Activating Token Index: 986

Text #1

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6731. Min Act: -0.1700

Data Index: 8093797 (Open Web Text)

Max Activating Token Index: 128

Text #2

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6802. Min Act: -0.1699

Data Index: 8047288 (Open Web Text)

Max Activating Token Index: 543

Text #3

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6616. Min Act: -0.1700

Data Index: 12186 (Open Web Text)

Max Activating Token Index: 1021

Text #4

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6586. Min Act: -0.1700

Data Index: 5874994 (Open Web Text)

Max Activating Token Index: 224

Text #5

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6575. Min Act: -0.1700

Data Index: 2198562 (Open Web Text)

Max Activating Token Index: 177

Text #6

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6594. Min Act: -0.1700

Data Index: 2613279 (Open Web Text)

Max Activating Token Index: 430

Text #7

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6528. Min Act: -0.1697

Data Index: 4430236 (Open Web Text)

Max Activating Token Index: 125

Text #8

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6571. Min Act: -0.1700

Data Index: 5810596 (Open Web Text)

Max Activating Token Index: 63

Text #9

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6402. Min Act: -0.1700

Data Index: 259647 (Open Web Text)

Max Activating Token Index: 459

Text #10

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6481. Min Act: -0.1700

Data Index: 6131021 (Open Web Text)

Max Activating Token Index: 110

Text #11

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6422. Min Act: -0.1700

Data Index: 4591595 (Open Web Text)

Max Activating Token Index: 662

Text #12

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6359. Min Act: -0.1700

Data Index: 424785 (Open Web Text)

Max Activating Token Index: 973

Text #13

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6393. Min Act: -0.1699

Data Index: 3479302 (Open Web Text)

Max Activating Token Index: 1021

Text #14

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6356. Min Act: -0.1700

Data Index: 6769896 (Open Web Text)

Max Activating Token Index: 71

Text #15

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6350. Min Act: -0.1700

Data Index: 8630916 (Open Web Text)

Max Activating Token Index: 395

Text #16

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6355. Min Act: -0.1698

Data Index: 7266339 (Open Web Text)

Max Activating Token Index: 71

Text #17

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6382. Min Act: -0.1700

Data Index: 1397426 (Open Web Text)

Max Activating Token Index: 49

Text #18

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6246. Min Act: -0.1700

Data Index: 7240858 (Open Web Text)

Max Activating Token Index: 993

Text #19

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6290. Min Act: -0.1700

Data Index: 7914923 (Open Web Text)

Max Activating Token Index: 118