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

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

Neuron 1646 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: 0.2176. Min Range: -0.2176

Max Act: 0.2078. Min Act: -0.0001

Data Index: 1596324 (Python Code)

Max Activating Token Index: 747

Text #1

Max Range: 0.2176. Min Range: -0.2176

Max Act: 0.2176. Min Act: -0.0001

Data Index: 1624503 (Python Code)

Max Activating Token Index: 988

Text #2

Max Range: 0.2176. Min Range: -0.2176

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1366803 (Python Code)

Max Activating Token Index: 183

Text #3

Max Range: 0.2176. Min Range: -0.2176

Max Act: 0.1732. Min Act: -0.0000

Data Index: 1387389 (Python Code)

Max Activating Token Index: 323

Text #4

Max Range: 0.2176. Min Range: -0.2176

Max Act: 0.1608. Min Act: -0.0001

Data Index: 1468669 (Python Code)

Max Activating Token Index: 1005

Text #5

Max Range: 0.2176. Min Range: -0.2176

Max Act: 0.1694. Min Act: -0.0001

Data Index: 1618634 (Python Code)

Max Activating Token Index: 983

Text #6

Max Range: 0.2176. Min Range: -0.2176

Max Act: 0.1713. Min Act: -0.0001

Data Index: 1490210 (Python Code)

Max Activating Token Index: 714

Text #7

Max Range: 0.2176. Min Range: -0.2176

Max Act: 0.1636. Min Act: -0.0000

Data Index: 1510797 (Python Code)

Max Activating Token Index: 556

Text #8

Max Range: 0.2176. Min Range: -0.2176

Max Act: 0.1626. Min Act: -0.0001

Data Index: 1373297 (Python Code)

Max Activating Token Index: 750

Text #9

Max Range: 0.2176. Min Range: -0.2176

Max Act: 0.1631. Min Act: -0.0001

Data Index: 1461823 (Python Code)

Max Activating Token Index: 244

Text #10

Max Range: 0.2176. Min Range: -0.2176

Max Act: 0.1328. Min Act: -0.0001

Data Index: 1036551 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.2176. Min Range: -0.2176

Max Act: 0.1497. Min Act: -0.0000

Data Index: 1426639 (Python Code)

Max Activating Token Index: 943

Text #12

Max Range: 0.2176. Min Range: -0.2176

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1564915 (Python Code)

Max Activating Token Index: 1017

Text #13

Max Range: 0.2176. Min Range: -0.2176

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1548029 (Python Code)

Max Activating Token Index: 436

Text #14

Max Range: 0.2176. Min Range: -0.2176

Max Act: 0.1581. Min Act: -0.0001

Data Index: 1106485 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.2176. Min Range: -0.2176

Max Act: 0.1668. Min Act: -0.0001

Data Index: 1527470 (Python Code)

Max Activating Token Index: 195

Text #16

Max Range: 0.2176. Min Range: -0.2176

Max Act: 0.1586. Min Act: -0.0001

Data Index: 251228 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.2176. Min Range: -0.2176

Max Act: 0.1550. Min Act: -0.0001

Data Index: 1048449 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.2176. Min Range: -0.2176

Max Act: 0.1490. Min Act: -0.0001

Data Index: 545377 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.2176. Min Range: -0.2176

Max Act: 0.1346. Min Act: -0.0000

Data Index: 1505432 (Python Code)

Max Activating Token Index: 526