Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4135 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.5865. Min Act: -0.0000

Data Index: 1561701 (Python Code)

Max Activating Token Index: 354

Text #1

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.4486. Min Act: -0.0000

Data Index: 1368292 (Python Code)

Max Activating Token Index: 201

Text #2

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.3710. Min Act: -0.0000

Data Index: 1403756 (Python Code)

Max Activating Token Index: 564

Text #3

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.4898. Min Act: -0.0000

Data Index: 1589040 (Python Code)

Max Activating Token Index: 860

Text #4

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.2083. Min Act: -0.0000

Data Index: 1529205 (Python Code)

Max Activating Token Index: 767

Text #5

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.2778. Min Act: -0.0000

Data Index: 1471411 (Python Code)

Max Activating Token Index: 713

Text #6

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.2161. Min Act: -0.0000

Data Index: 1551271 (Python Code)

Max Activating Token Index: 154

Text #7

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.1959. Min Act: -0.0000

Data Index: 1568982 (Python Code)

Max Activating Token Index: 742

Text #8

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.2007. Min Act: -0.0000

Data Index: 1645417 (Python Code)

Max Activating Token Index: 330

Text #9

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.0975. Min Act: -0.0000

Data Index: 1432098 (Python Code)

Max Activating Token Index: 552

Text #10

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.0315. Min Act: -0.0000

Data Index: 1553120 (Python Code)

Max Activating Token Index: 629

Text #11

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.0196. Min Act: -0.0000

Data Index: 1602201 (Python Code)

Max Activating Token Index: 335

Text #12

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.0359. Min Act: -0.0000

Data Index: 1533631 (Python Code)

Max Activating Token Index: 565

Text #13

Max Range: 2.5865. Min Range: -2.5865

Max Act: 1.7964. Min Act: -0.0000

Data Index: 1577400 (Python Code)

Max Activating Token Index: 279

Text #14

Max Range: 2.5865. Min Range: -2.5865

Max Act: 1.8835. Min Act: -0.0000

Data Index: 1569932 (Python Code)

Max Activating Token Index: 861

Text #15

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.0804. Min Act: -0.0000

Data Index: 1460243 (Python Code)

Max Activating Token Index: 535

Text #16

Max Range: 2.5865. Min Range: -2.5865

Max Act: 1.9199. Min Act: -0.0000

Data Index: 1608197 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.0146. Min Act: -0.0000

Data Index: 1566920 (Python Code)

Max Activating Token Index: 706

Text #18

Max Range: 2.5865. Min Range: -2.5865

Max Act: 1.8830. Min Act: -0.0000

Data Index: 1654387 (Python Code)

Max Activating Token Index: 624

Text #19

Max Range: 2.5865. Min Range: -2.5865

Max Act: 1.8785. Min Act: -0.0000

Data Index: 1432954 (Python Code)

Max Activating Token Index: 458