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

Dataset: Open Web Text

Neuron 631 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: 6.6189. Min Range: -6.6189

Max Act: 6.6189. Min Act: -0.1700

Data Index: 1033008 (Open Web Text)

Max Activating Token Index: 211

Text #1

Max Range: 6.6189. Min Range: -6.6189

Max Act: 6.5344. Min Act: -0.1700

Data Index: 206410 (Open Web Text)

Max Activating Token Index: 444

Text #2

Max Range: 6.6189. Min Range: -6.6189

Max Act: 6.4783. Min Act: -0.1700

Data Index: 1375923 (Open Web Text)

Max Activating Token Index: 73

Text #3

Max Range: 6.6189. Min Range: -6.6189

Max Act: 6.3177. Min Act: -0.1700

Data Index: 5631731 (Open Web Text)

Max Activating Token Index: 301

Text #4

Max Range: 6.6189. Min Range: -6.6189

Max Act: 6.3740. Min Act: -0.1700

Data Index: 2799313 (Open Web Text)

Max Activating Token Index: 678

Text #5

Max Range: 6.6189. Min Range: -6.6189

Max Act: 6.3317. Min Act: -0.1700

Data Index: 2972426 (Open Web Text)

Max Activating Token Index: 636

Text #6

Max Range: 6.6189. Min Range: -6.6189

Max Act: 6.3604. Min Act: -0.1700

Data Index: 3939846 (Open Web Text)

Max Activating Token Index: 696

Text #7

Max Range: 6.6189. Min Range: -6.6189

Max Act: 6.2884. Min Act: -0.1700

Data Index: 6580861 (Open Web Text)

Max Activating Token Index: 294

Text #8

Max Range: 6.6189. Min Range: -6.6189

Max Act: 6.3095. Min Act: -0.1700

Data Index: 5669822 (Open Web Text)

Max Activating Token Index: 586

Text #9

Max Range: 6.6189. Min Range: -6.6189

Max Act: 6.3066. Min Act: -0.1700

Data Index: 8068730 (Open Web Text)

Max Activating Token Index: 662

Text #10

Max Range: 6.6189. Min Range: -6.6189

Max Act: 6.2543. Min Act: -0.1700

Data Index: 7060492 (Open Web Text)

Max Activating Token Index: 393

Text #11

Max Range: 6.6189. Min Range: -6.6189

Max Act: 6.3031. Min Act: -0.1700

Data Index: 4594860 (Open Web Text)

Max Activating Token Index: 184

Text #12

Max Range: 6.6189. Min Range: -6.6189

Max Act: 6.3413. Min Act: -0.1700

Data Index: 6906650 (Open Web Text)

Max Activating Token Index: 810

Text #13

Max Range: 6.6189. Min Range: -6.6189

Max Act: 6.3257. Min Act: -0.1700

Data Index: 4047955 (Open Web Text)

Max Activating Token Index: 920

Text #14

Max Range: 6.6189. Min Range: -6.6189

Max Act: 6.2705. Min Act: -0.1700

Data Index: 8605883 (Open Web Text)

Max Activating Token Index: 660

Text #15

Max Range: 6.6189. Min Range: -6.6189

Max Act: 6.2932. Min Act: -0.1700

Data Index: 3314514 (Open Web Text)

Max Activating Token Index: 928

Text #16

Max Range: 6.6189. Min Range: -6.6189

Max Act: 6.2086. Min Act: -0.1700

Data Index: 4938350 (Open Web Text)

Max Activating Token Index: 736

Text #17

Max Range: 6.6189. Min Range: -6.6189

Max Act: 6.2587. Min Act: -0.1700

Data Index: 5206698 (Open Web Text)

Max Activating Token Index: 838

Text #18

Max Range: 6.6189. Min Range: -6.6189

Max Act: 6.2763. Min Act: -0.1700

Data Index: 4882802 (Open Web Text)

Max Activating Token Index: 603

Text #19

Max Range: 6.6189. Min Range: -6.6189

Max Act: 6.1819. Min Act: -0.1700

Data Index: 2457162 (Open Web Text)

Max Activating Token Index: 291