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

Dataset: Open Web Text

Neuron 2004 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: 4.2393. Min Range: -4.2393

Max Act: 4.2393. Min Act: -0.1700

Data Index: 330562 (Open Web Text)

Max Activating Token Index: 19

Text #1

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.1359. Min Act: -0.1700

Data Index: 714949 (Open Web Text)

Max Activating Token Index: 34

Text #2

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.1378. Min Act: -0.1700

Data Index: 7464978 (Open Web Text)

Max Activating Token Index: 561

Text #3

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0917. Min Act: -0.1700

Data Index: 4242656 (Open Web Text)

Max Activating Token Index: 617

Text #4

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.1109. Min Act: -0.1700

Data Index: 5049377 (Open Web Text)

Max Activating Token Index: 281

Text #5

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.1072. Min Act: -0.1700

Data Index: 7950981 (Open Web Text)

Max Activating Token Index: 343

Text #6

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0870. Min Act: -0.1700

Data Index: 3799211 (Open Web Text)

Max Activating Token Index: 710

Text #7

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0740. Min Act: -0.1700

Data Index: 3500445 (Open Web Text)

Max Activating Token Index: 27

Text #8

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0686. Min Act: -0.1700

Data Index: 8818743 (Open Web Text)

Max Activating Token Index: 364

Text #9

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0580. Min Act: -0.1700

Data Index: 8177062 (Open Web Text)

Max Activating Token Index: 329

Text #10

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0775. Min Act: -0.1699

Data Index: 547340 (Open Web Text)

Max Activating Token Index: 196

Text #11

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0886. Min Act: -0.1700

Data Index: 7695720 (Open Web Text)

Max Activating Token Index: 584

Text #12

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0621. Min Act: -0.1700

Data Index: 6281406 (Open Web Text)

Max Activating Token Index: 107

Text #13

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0637. Min Act: -0.1700

Data Index: 5574311 (Open Web Text)

Max Activating Token Index: 332

Text #14

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0706. Min Act: -0.1700

Data Index: 4548149 (Open Web Text)

Max Activating Token Index: 25

Text #15

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0703. Min Act: -0.1700

Data Index: 4285452 (Open Web Text)

Max Activating Token Index: 654

Text #16

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0440. Min Act: -0.1700

Data Index: 2992887 (Open Web Text)

Max Activating Token Index: 501

Text #17

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0456. Min Act: -0.1700

Data Index: 3461690 (Open Web Text)

Max Activating Token Index: 365

Text #18

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0383. Min Act: -0.1700

Data Index: 3624584 (Open Web Text)

Max Activating Token Index: 287

Text #19

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0354. Min Act: -0.1700

Data Index: 38215 (Open Web Text)

Max Activating Token Index: 40