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

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

Neuron 1217 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.6177. Min Act: -0.0001

Data Index: 1643456 (Python Code)

Max Activating Token Index: 250

Text #1

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.4656. Min Act: -0.0000

Data Index: 1594130 (Python Code)

Max Activating Token Index: 570

Text #2

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.4637. Min Act: -0.0001

Data Index: 1419058 (Python Code)

Max Activating Token Index: 960

Text #3

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.3961. Min Act: -0.0000

Data Index: 1656917 (Python Code)

Max Activating Token Index: 236

Text #4

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.4083. Min Act: -0.0000

Data Index: 1485216 (Python Code)

Max Activating Token Index: 770

Text #5

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.2512. Min Act: -0.0001

Data Index: 1430618 (Python Code)

Max Activating Token Index: 957

Text #6

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.1907. Min Act: -0.0000

Data Index: 1578369 (Python Code)

Max Activating Token Index: 767

Text #7

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.2576. Min Act: -0.0000

Data Index: 176528 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.2150. Min Act: -0.0000

Data Index: 1574500 (Python Code)

Max Activating Token Index: 228

Text #9

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.1741. Min Act: -0.0001

Data Index: 596142 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.1722. Min Act: -0.0000

Data Index: 1612469 (Python Code)

Max Activating Token Index: 147

Text #11

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.1431. Min Act: -0.0000

Data Index: 1484491 (Python Code)

Max Activating Token Index: 960

Text #12

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.1676. Min Act: -0.0000

Data Index: 1403424 (Python Code)

Max Activating Token Index: 389

Text #13

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.1891. Min Act: -0.0001

Data Index: 1559841 (Python Code)

Max Activating Token Index: 486

Text #14

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.2054. Min Act: -0.0001

Data Index: 1619137 (Python Code)

Max Activating Token Index: 96

Text #15

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.1613. Min Act: -0.0000

Data Index: 46299 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.1524. Min Act: -0.0001

Data Index: 1505626 (Python Code)

Max Activating Token Index: 150

Text #17

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.1383. Min Act: -0.0000

Data Index: 699643 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.1650. Min Act: -0.0001

Data Index: 1438392 (Python Code)

Max Activating Token Index: 347

Text #19

Max Range: 1.6177. Min Range: -1.6177

Max Act: 1.0698. Min Act: -0.0000

Data Index: 867713 (C4 (Web Text))

Max Activating Token Index: 463