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

Dataset: Open Web Text

Neuron 2199 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: 3.7705. Min Range: -3.7705

Max Act: 3.7566. Min Act: -0.1700

Data Index: 6678700 (Open Web Text)

Max Activating Token Index: 671

Text #1

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.7705. Min Act: -0.1700

Data Index: 352199 (Open Web Text)

Max Activating Token Index: 727

Text #2

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.7275. Min Act: -0.1700

Data Index: 3177487 (Open Web Text)

Max Activating Token Index: 642

Text #3

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.6310. Min Act: -0.1700

Data Index: 368910 (Open Web Text)

Max Activating Token Index: 310

Text #4

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.6018. Min Act: -0.1700

Data Index: 5824709 (Open Web Text)

Max Activating Token Index: 733

Text #5

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.6063. Min Act: -0.1700

Data Index: 7351881 (Open Web Text)

Max Activating Token Index: 363

Text #6

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.5835. Min Act: -0.1700

Data Index: 2415180 (Open Web Text)

Max Activating Token Index: 177

Text #7

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.5980. Min Act: -0.1700

Data Index: 3381165 (Open Web Text)

Max Activating Token Index: 968

Text #8

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.5734. Min Act: -0.1700

Data Index: 2526004 (Open Web Text)

Max Activating Token Index: 936

Text #9

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.5828. Min Act: -0.1700

Data Index: 5847858 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.5685. Min Act: -0.1700

Data Index: 3229198 (Open Web Text)

Max Activating Token Index: 155

Text #11

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.5440. Min Act: -0.1700

Data Index: 6353660 (Open Web Text)

Max Activating Token Index: 382

Text #12

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.5131. Min Act: -0.1700

Data Index: 900663 (Open Web Text)

Max Activating Token Index: 323

Text #13

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.5422. Min Act: -0.1700

Data Index: 8416185 (Open Web Text)

Max Activating Token Index: 781

Text #14

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.4838. Min Act: -0.1700

Data Index: 2186773 (Open Web Text)

Max Activating Token Index: 1005

Text #15

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.4361. Min Act: -0.1700

Data Index: 7074881 (Open Web Text)

Max Activating Token Index: 572

Text #16

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.5037. Min Act: -0.1700

Data Index: 5170685 (Open Web Text)

Max Activating Token Index: 930

Text #17

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.4786. Min Act: -0.1700

Data Index: 2042110 (Open Web Text)

Max Activating Token Index: 735

Text #18

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.5186. Min Act: -0.1700

Data Index: 6925501 (Open Web Text)

Max Activating Token Index: 878

Text #19

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.4897. Min Act: -0.1700

Data Index: 856629 (Open Web Text)

Max Activating Token Index: 105