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

Dataset: Open Web Text

Neuron 1263 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: 4.0480. Min Range: -4.0480

Max Act: 4.0460. Min Act: -0.1700

Data Index: 5356712 (Open Web Text)

Max Activating Token Index: 15

Text #1

Max Range: 4.0480. Min Range: -4.0480

Max Act: 4.0480. Min Act: -0.1700

Data Index: 6105292 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.0480. Min Range: -4.0480

Max Act: 4.0290. Min Act: -0.1696

Data Index: 1027157 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.0480. Min Range: -4.0480

Max Act: 4.0240. Min Act: -0.1700

Data Index: 1167354 (Open Web Text)

Max Activating Token Index: 42

Text #4

Max Range: 4.0480. Min Range: -4.0480

Max Act: 4.0101. Min Act: -0.1693

Data Index: 685370 (Open Web Text)

Max Activating Token Index: 79

Text #5

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.9863. Min Act: -0.1700

Data Index: 2200417 (Open Web Text)

Max Activating Token Index: 45

Text #6

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.9761. Min Act: -0.1700

Data Index: 4047525 (Open Web Text)

Max Activating Token Index: 63

Text #7

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.9643. Min Act: -0.1695

Data Index: 1902664 (Open Web Text)

Max Activating Token Index: 26

Text #8

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.9655. Min Act: -0.1700

Data Index: 2003424 (Open Web Text)

Max Activating Token Index: 37

Text #9

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.9968. Min Act: -0.1696

Data Index: 6531612 (Open Web Text)

Max Activating Token Index: 39

Text #10

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.9738. Min Act: -0.1700

Data Index: 6939203 (Open Web Text)

Max Activating Token Index: 40

Text #11

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.9247. Min Act: -0.1700

Data Index: 1004838 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.9351. Min Act: -0.1700

Data Index: 412930 (Open Web Text)

Max Activating Token Index: 55

Text #13

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.9385. Min Act: -0.1700

Data Index: 5377232 (Open Web Text)

Max Activating Token Index: 19

Text #14

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.9452. Min Act: -0.1700

Data Index: 5912806 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.9314. Min Act: -0.1700

Data Index: 5357287 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.9601. Min Act: -0.1694

Data Index: 4407173 (Open Web Text)

Max Activating Token Index: 34

Text #17

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.9529. Min Act: -0.1688

Data Index: 2872605 (Open Web Text)

Max Activating Token Index: 37

Text #18

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.9373. Min Act: -0.1700

Data Index: 20578 (Open Web Text)

Max Activating Token Index: 52

Text #19

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.9339. Min Act: -0.1700

Data Index: 4634818 (Open Web Text)

Max Activating Token Index: 30