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

Dataset: Open Web Text

Neuron 523 in Layer 3

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: 3.5864. Min Range: -3.5864

Max Act: 3.5546. Min Act: -0.1700

Data Index: 7306056 (Open Web Text)

Max Activating Token Index: 766

Text #1

Max Range: 3.5864. Min Range: -3.5864

Max Act: 3.5864. Min Act: -0.1700

Data Index: 5753737 (Open Web Text)

Max Activating Token Index: 551

Text #2

Max Range: 3.5864. Min Range: -3.5864

Max Act: 3.5680. Min Act: -0.1700

Data Index: 8161118 (Open Web Text)

Max Activating Token Index: 336

Text #3

Max Range: 3.5864. Min Range: -3.5864

Max Act: 3.5548. Min Act: -0.1700

Data Index: 7306057 (Open Web Text)

Max Activating Token Index: 776

Text #4

Max Range: 3.5864. Min Range: -3.5864

Max Act: 3.5280. Min Act: -0.1700

Data Index: 6366026 (Open Web Text)

Max Activating Token Index: 700

Text #5

Max Range: 3.5864. Min Range: -3.5864

Max Act: 3.5253. Min Act: -0.1700

Data Index: 6309838 (Open Web Text)

Max Activating Token Index: 870

Text #6

Max Range: 3.5864. Min Range: -3.5864

Max Act: 3.5262. Min Act: -0.1700

Data Index: 6309839 (Open Web Text)

Max Activating Token Index: 597

Text #7

Max Range: 3.5864. Min Range: -3.5864

Max Act: 3.5059. Min Act: -0.1700

Data Index: 2208357 (Open Web Text)

Max Activating Token Index: 196

Text #8

Max Range: 3.5864. Min Range: -3.5864

Max Act: 3.5322. Min Act: -0.1700

Data Index: 4018207 (Open Web Text)

Max Activating Token Index: 616

Text #9

Max Range: 3.5864. Min Range: -3.5864

Max Act: 3.5190. Min Act: -0.1700

Data Index: 1444839 (Open Web Text)

Max Activating Token Index: 844

Text #10

Max Range: 3.5864. Min Range: -3.5864

Max Act: 3.5127. Min Act: -0.1700

Data Index: 5275929 (Open Web Text)

Max Activating Token Index: 454

Text #11

Max Range: 3.5864. Min Range: -3.5864

Max Act: 3.4775. Min Act: -0.1700

Data Index: 6366025 (Open Web Text)

Max Activating Token Index: 653

Text #12

Max Range: 3.5864. Min Range: -3.5864

Max Act: 3.4644. Min Act: -0.1700

Data Index: 2179652 (Open Web Text)

Max Activating Token Index: 735

Text #13

Max Range: 3.5864. Min Range: -3.5864

Max Act: 3.4508. Min Act: -0.1700

Data Index: 526609 (Open Web Text)

Max Activating Token Index: 564

Text #14

Max Range: 3.5864. Min Range: -3.5864

Max Act: 3.4559. Min Act: -0.1700

Data Index: 7769763 (Open Web Text)

Max Activating Token Index: 772

Text #15

Max Range: 3.5864. Min Range: -3.5864

Max Act: 3.4551. Min Act: -0.1700

Data Index: 597642 (Open Web Text)

Max Activating Token Index: 570

Text #16

Max Range: 3.5864. Min Range: -3.5864

Max Act: 3.4472. Min Act: -0.1700

Data Index: 39604 (Open Web Text)

Max Activating Token Index: 726

Text #17

Max Range: 3.5864. Min Range: -3.5864

Max Act: 3.4307. Min Act: -0.1700

Data Index: 6309837 (Open Web Text)

Max Activating Token Index: 899

Text #18

Max Range: 3.5864. Min Range: -3.5864

Max Act: 3.4327. Min Act: -0.1700

Data Index: 4681619 (Open Web Text)

Max Activating Token Index: 654

Text #19

Max Range: 3.5864. Min Range: -3.5864

Max Act: 3.4217. Min Act: -0.1700

Data Index: 845922 (Open Web Text)

Max Activating Token Index: 436