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

Dataset: Open Web Text

Neuron 2440 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: 0.8582. Min Range: -0.8582

Max Act: 0.8510. Min Act: -0.1406

Data Index: 7787036 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8521. Min Act: -0.1682

Data Index: 5390350 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8582. Min Act: -0.1517

Data Index: 8290903 (Open Web Text)

Max Activating Token Index: 502

Text #3

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8508. Min Act: -0.1553

Data Index: 2953268 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8471. Min Act: -0.1670

Data Index: 8391092 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8488. Min Act: -0.1518

Data Index: 2534292 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8428. Min Act: -0.1620

Data Index: 2534528 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8406. Min Act: -0.1549

Data Index: 2811915 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8329. Min Act: -0.1615

Data Index: 7068275 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8361. Min Act: -0.1674

Data Index: 2037941 (Open Web Text)

Max Activating Token Index: 465

Text #10

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8322. Min Act: -0.1482

Data Index: 3616011 (Open Web Text)

Max Activating Token Index: 97

Text #11

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8344. Min Act: -0.1497

Data Index: 8623017 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8310. Min Act: -0.1654

Data Index: 4466523 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8310. Min Act: -0.1344

Data Index: 8826200 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8318. Min Act: -0.1476

Data Index: 4254325 (Open Web Text)

Max Activating Token Index: 677

Text #15

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8271. Min Act: -0.1382

Data Index: 5802949 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8247. Min Act: -0.1609

Data Index: 7338336 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8249. Min Act: -0.1417

Data Index: 4279388 (Open Web Text)

Max Activating Token Index: 486

Text #18

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8244. Min Act: -0.1558

Data Index: 7146057 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8220. Min Act: -0.1637

Data Index: 1358614 (Open Web Text)

Max Activating Token Index: 93