Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4271 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1649. Min Act: -0.0001

Data Index: 152735 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1562. Min Act: -0.0001

Data Index: 327291 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1410. Min Act: -0.0001

Data Index: 1050862 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1066119 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1559. Min Act: -0.0001

Data Index: 1205150 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1438. Min Act: -0.0001

Data Index: 498514 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1142. Min Act: -0.0001

Data Index: 759532 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1217. Min Act: -0.0001

Data Index: 377181 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1332. Min Act: -0.0001

Data Index: 1178499 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1416. Min Act: -0.0001

Data Index: 184811 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1193781 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1366. Min Act: -0.0000

Data Index: 398779 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1515. Min Act: -0.0000

Data Index: 844142 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1512. Min Act: -0.0001

Data Index: 896171 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1463. Min Act: -0.0001

Data Index: 988094 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1353. Min Act: -0.0001

Data Index: 952750 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1387. Min Act: -0.0001

Data Index: 1289789 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1240. Min Act: -0.0000

Data Index: 479617 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1432. Min Act: -0.0000

Data Index: 926167 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1435. Min Act: -0.0001

Data Index: 860569 (C4 (Web Text))

Max Activating Token Index: 928