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

Dataset: Open Web Text

Neuron 1536 in Layer 4

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: 4.2997. Min Range: -4.2997

Max Act: 4.2997. Min Act: -0.1700

Data Index: 1349810 (Open Web Text)

Max Activating Token Index: 612

Text #1

Max Range: 4.2997. Min Range: -4.2997

Max Act: 4.2729. Min Act: -0.1700

Data Index: 1436263 (Open Web Text)

Max Activating Token Index: 501

Text #2

Max Range: 4.2997. Min Range: -4.2997

Max Act: 4.2592. Min Act: -0.1700

Data Index: 4181758 (Open Web Text)

Max Activating Token Index: 666

Text #3

Max Range: 4.2997. Min Range: -4.2997

Max Act: 4.2726. Min Act: -0.1700

Data Index: 1834156 (Open Web Text)

Max Activating Token Index: 974

Text #4

Max Range: 4.2997. Min Range: -4.2997

Max Act: 4.2392. Min Act: -0.1700

Data Index: 3406389 (Open Web Text)

Max Activating Token Index: 572

Text #5

Max Range: 4.2997. Min Range: -4.2997

Max Act: 4.1797. Min Act: -0.1700

Data Index: 6015785 (Open Web Text)

Max Activating Token Index: 465

Text #6

Max Range: 4.2997. Min Range: -4.2997

Max Act: 4.2178. Min Act: -0.1700

Data Index: 86987 (Open Web Text)

Max Activating Token Index: 598

Text #7

Max Range: 4.2997. Min Range: -4.2997

Max Act: 4.1920. Min Act: -0.1700

Data Index: 4975568 (Open Web Text)

Max Activating Token Index: 712

Text #8

Max Range: 4.2997. Min Range: -4.2997

Max Act: 4.1634. Min Act: -0.1700

Data Index: 2093069 (Open Web Text)

Max Activating Token Index: 387

Text #9

Max Range: 4.2997. Min Range: -4.2997

Max Act: 4.1398. Min Act: -0.1700

Data Index: 4736972 (Open Web Text)

Max Activating Token Index: 814

Text #10

Max Range: 4.2997. Min Range: -4.2997

Max Act: 4.1434. Min Act: -0.1700

Data Index: 6157657 (Open Web Text)

Max Activating Token Index: 330

Text #11

Max Range: 4.2997. Min Range: -4.2997

Max Act: 4.1876. Min Act: -0.1700

Data Index: 860317 (Open Web Text)

Max Activating Token Index: 829

Text #12

Max Range: 4.2997. Min Range: -4.2997

Max Act: 4.1312. Min Act: -0.1700

Data Index: 4938719 (Open Web Text)

Max Activating Token Index: 418

Text #13

Max Range: 4.2997. Min Range: -4.2997

Max Act: 4.1448. Min Act: -0.1700

Data Index: 8546938 (Open Web Text)

Max Activating Token Index: 573

Text #14

Max Range: 4.2997. Min Range: -4.2997

Max Act: 4.1449. Min Act: -0.1700

Data Index: 8269503 (Open Web Text)

Max Activating Token Index: 887

Text #15

Max Range: 4.2997. Min Range: -4.2997

Max Act: 4.1369. Min Act: -0.1700

Data Index: 7826962 (Open Web Text)

Max Activating Token Index: 683

Text #16

Max Range: 4.2997. Min Range: -4.2997

Max Act: 4.1372. Min Act: -0.1700

Data Index: 3038869 (Open Web Text)

Max Activating Token Index: 239

Text #17

Max Range: 4.2997. Min Range: -4.2997

Max Act: 4.1513. Min Act: -0.1700

Data Index: 706604 (Open Web Text)

Max Activating Token Index: 300

Text #18

Max Range: 4.2997. Min Range: -4.2997

Max Act: 4.1484. Min Act: -0.1700

Data Index: 322338 (Open Web Text)

Max Activating Token Index: 179

Text #19

Max Range: 4.2997. Min Range: -4.2997

Max Act: 4.1395. Min Act: -0.1700

Data Index: 6787156 (Open Web Text)

Max Activating Token Index: 608