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

Dataset: Open Web Text

Neuron 737 in Layer 2

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: 4.0474. Min Range: -4.0474

Max Act: 4.0474. Min Act: -0.1700

Data Index: 6088900 (Open Web Text)

Max Activating Token Index: 435

Text #1

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.9797. Min Act: -0.1700

Data Index: 628843 (Open Web Text)

Max Activating Token Index: 280

Text #2

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8654. Min Act: -0.1700

Data Index: 8470519 (Open Web Text)

Max Activating Token Index: 908

Text #3

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8930. Min Act: -0.1700

Data Index: 6727063 (Open Web Text)

Max Activating Token Index: 421

Text #4

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8455. Min Act: -0.1700

Data Index: 872385 (Open Web Text)

Max Activating Token Index: 749

Text #5

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8356. Min Act: -0.1700

Data Index: 5070825 (Open Web Text)

Max Activating Token Index: 643

Text #6

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8629. Min Act: -0.1700

Data Index: 7504818 (Open Web Text)

Max Activating Token Index: 873

Text #7

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8627. Min Act: -0.1700

Data Index: 6918912 (Open Web Text)

Max Activating Token Index: 216

Text #8

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8549. Min Act: -0.1700

Data Index: 3722142 (Open Web Text)

Max Activating Token Index: 968

Text #9

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8636. Min Act: -0.1700

Data Index: 5475431 (Open Web Text)

Max Activating Token Index: 27

Text #10

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8620. Min Act: -0.1700

Data Index: 5479116 (Open Web Text)

Max Activating Token Index: 773

Text #11

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8290. Min Act: -0.1700

Data Index: 3916458 (Open Web Text)

Max Activating Token Index: 624

Text #12

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8233. Min Act: -0.1700

Data Index: 6841207 (Open Web Text)

Max Activating Token Index: 492

Text #13

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.7935. Min Act: -0.1700

Data Index: 2531204 (Open Web Text)

Max Activating Token Index: 886

Text #14

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.7751. Min Act: -0.1700

Data Index: 7724710 (Open Web Text)

Max Activating Token Index: 399

Text #15

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8213. Min Act: -0.1700

Data Index: 4133103 (Open Web Text)

Max Activating Token Index: 704

Text #16

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8196. Min Act: -0.1700

Data Index: 3556855 (Open Web Text)

Max Activating Token Index: 528

Text #17

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8506. Min Act: -0.1700

Data Index: 506877 (Open Web Text)

Max Activating Token Index: 617

Text #18

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8266. Min Act: -0.1700

Data Index: 4471370 (Open Web Text)

Max Activating Token Index: 1003

Text #19

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8170. Min Act: -0.1700

Data Index: 6795580 (Open Web Text)

Max Activating Token Index: 219