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

Dataset: Open Web Text

Neuron 226 in Layer 1

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: 0.8066. Min Range: -0.8066

Max Act: 0.8066. Min Act: -0.1655

Data Index: 2964133 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7634. Min Act: -0.1698

Data Index: 6325549 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7526. Min Act: -0.1697

Data Index: 6326608 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7525. Min Act: -0.1347

Data Index: 3691237 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7486. Min Act: -0.1687

Data Index: 2805258 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7378. Min Act: -0.1697

Data Index: 2209743 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7486. Min Act: -0.1698

Data Index: 8665787 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7486. Min Act: -0.1690

Data Index: 8264508 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7486. Min Act: -0.1621

Data Index: 4529372 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7486. Min Act: -0.1356

Data Index: 7734543 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7440. Min Act: -0.1403

Data Index: 6457591 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7486. Min Act: -0.1600

Data Index: 2215319 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7385. Min Act: -0.1498

Data Index: 425622 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7385. Min Act: -0.1645

Data Index: 1805240 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7385. Min Act: -0.1583

Data Index: 3883148 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7385. Min Act: -0.1354

Data Index: 4952193 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7360. Min Act: -0.1664

Data Index: 1236233 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7385. Min Act: -0.1522

Data Index: 5531996 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7341. Min Act: -0.1638

Data Index: 4291891 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7385. Min Act: -0.1389

Data Index: 5880512 (Open Web Text)

Max Activating Token Index: 3