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

Dataset: Open Web Text

Neuron 2725 in Layer 5

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: 3.6857. Min Range: -3.6857

Max Act: 3.6857. Min Act: -0.1700

Data Index: 6061156 (Open Web Text)

Max Activating Token Index: 437

Text #1

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.6130. Min Act: -0.1700

Data Index: 1570767 (Open Web Text)

Max Activating Token Index: 938

Text #2

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.5753. Min Act: -0.1700

Data Index: 1767346 (Open Web Text)

Max Activating Token Index: 868

Text #3

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.6047. Min Act: -0.1700

Data Index: 2130530 (Open Web Text)

Max Activating Token Index: 790

Text #4

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.5338. Min Act: -0.1700

Data Index: 4162959 (Open Web Text)

Max Activating Token Index: 524

Text #5

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.5473. Min Act: -0.1700

Data Index: 144601 (Open Web Text)

Max Activating Token Index: 306

Text #6

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.5096. Min Act: -0.1700

Data Index: 5478987 (Open Web Text)

Max Activating Token Index: 970

Text #7

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4976. Min Act: -0.1700

Data Index: 2504612 (Open Web Text)

Max Activating Token Index: 455

Text #8

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4812. Min Act: -0.1700

Data Index: 8781639 (Open Web Text)

Max Activating Token Index: 651

Text #9

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4685. Min Act: -0.1700

Data Index: 3598012 (Open Web Text)

Max Activating Token Index: 272

Text #10

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4916. Min Act: -0.1700

Data Index: 5977455 (Open Web Text)

Max Activating Token Index: 668

Text #11

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4814. Min Act: -0.1700

Data Index: 2538834 (Open Web Text)

Max Activating Token Index: 686

Text #12

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4588. Min Act: -0.1700

Data Index: 3779924 (Open Web Text)

Max Activating Token Index: 867

Text #13

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4576. Min Act: -0.1700

Data Index: 2504607 (Open Web Text)

Max Activating Token Index: 211

Text #14

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4671. Min Act: -0.1700

Data Index: 3783706 (Open Web Text)

Max Activating Token Index: 947

Text #15

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4460. Min Act: -0.1700

Data Index: 5576833 (Open Web Text)

Max Activating Token Index: 599

Text #16

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4403. Min Act: -0.1700

Data Index: 73319 (Open Web Text)

Max Activating Token Index: 448

Text #17

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4336. Min Act: -0.1700

Data Index: 2473036 (Open Web Text)

Max Activating Token Index: 848

Text #18

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4437. Min Act: -0.1700

Data Index: 3578708 (Open Web Text)

Max Activating Token Index: 314

Text #19

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4358. Min Act: -0.1700

Data Index: 7397107 (Open Web Text)

Max Activating Token Index: 1000