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

Dataset: Open Web Text

Neuron 2229 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: 4.2448. Min Range: -4.2448

Max Act: 4.2448. Min Act: -0.1700

Data Index: 5085027 (Open Web Text)

Max Activating Token Index: 283

Text #1

Max Range: 4.2448. Min Range: -4.2448

Max Act: 4.2387. Min Act: -0.1700

Data Index: 7367023 (Open Web Text)

Max Activating Token Index: 290

Text #2

Max Range: 4.2448. Min Range: -4.2448

Max Act: 4.2325. Min Act: -0.1700

Data Index: 4460604 (Open Web Text)

Max Activating Token Index: 908

Text #3

Max Range: 4.2448. Min Range: -4.2448

Max Act: 4.1851. Min Act: -0.1700

Data Index: 6615927 (Open Web Text)

Max Activating Token Index: 559

Text #4

Max Range: 4.2448. Min Range: -4.2448

Max Act: 4.1124. Min Act: -0.1700

Data Index: 7750395 (Open Web Text)

Max Activating Token Index: 503

Text #5

Max Range: 4.2448. Min Range: -4.2448

Max Act: 4.1424. Min Act: -0.1700

Data Index: 870482 (Open Web Text)

Max Activating Token Index: 718

Text #6

Max Range: 4.2448. Min Range: -4.2448

Max Act: 4.1564. Min Act: -0.1700

Data Index: 1723971 (Open Web Text)

Max Activating Token Index: 746

Text #7

Max Range: 4.2448. Min Range: -4.2448

Max Act: 4.0969. Min Act: -0.1700

Data Index: 4715136 (Open Web Text)

Max Activating Token Index: 121

Text #8

Max Range: 4.2448. Min Range: -4.2448

Max Act: 4.0643. Min Act: -0.1700

Data Index: 2679487 (Open Web Text)

Max Activating Token Index: 722

Text #9

Max Range: 4.2448. Min Range: -4.2448

Max Act: 4.0236. Min Act: -0.1700

Data Index: 1775345 (Open Web Text)

Max Activating Token Index: 68

Text #10

Max Range: 4.2448. Min Range: -4.2448

Max Act: 4.1003. Min Act: -0.1700

Data Index: 7713315 (Open Web Text)

Max Activating Token Index: 594

Text #11

Max Range: 4.2448. Min Range: -4.2448

Max Act: 4.0570. Min Act: -0.1700

Data Index: 2415759 (Open Web Text)

Max Activating Token Index: 70

Text #12

Max Range: 4.2448. Min Range: -4.2448

Max Act: 4.0252. Min Act: -0.1700

Data Index: 7858032 (Open Web Text)

Max Activating Token Index: 831

Text #13

Max Range: 4.2448. Min Range: -4.2448

Max Act: 4.0337. Min Act: -0.1700

Data Index: 8683775 (Open Web Text)

Max Activating Token Index: 743

Text #14

Max Range: 4.2448. Min Range: -4.2448

Max Act: 4.0083. Min Act: -0.1700

Data Index: 109236 (Open Web Text)

Max Activating Token Index: 948

Text #15

Max Range: 4.2448. Min Range: -4.2448

Max Act: 4.0257. Min Act: -0.1700

Data Index: 706125 (Open Web Text)

Max Activating Token Index: 126

Text #16

Max Range: 4.2448. Min Range: -4.2448

Max Act: 4.0454. Min Act: -0.1700

Data Index: 8419651 (Open Web Text)

Max Activating Token Index: 611

Text #17

Max Range: 4.2448. Min Range: -4.2448

Max Act: 4.0619. Min Act: -0.1700

Data Index: 2473679 (Open Web Text)

Max Activating Token Index: 477

Text #18

Max Range: 4.2448. Min Range: -4.2448

Max Act: 4.0253. Min Act: -0.1700

Data Index: 7588014 (Open Web Text)

Max Activating Token Index: 168

Text #19

Max Range: 4.2448. Min Range: -4.2448

Max Act: 4.0092. Min Act: -0.1700

Data Index: 3294578 (Open Web Text)

Max Activating Token Index: 92