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

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

Neuron 726 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: 1.7829. Min Range: -1.7829

Max Act: 1.7829. Min Act: -0.0000

Data Index: 1541442 (Python Code)

Max Activating Token Index: 509

Text #1

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.5808. Min Act: -0.0000

Data Index: 583366 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.5595. Min Act: -0.0000

Data Index: 1314913 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.4380. Min Act: -0.0000

Data Index: 1310320 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.5795. Min Act: -0.0000

Data Index: 152077 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.4680. Min Act: -0.0000

Data Index: 1596089 (Python Code)

Max Activating Token Index: 151

Text #6

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.4466. Min Act: -0.0000

Data Index: 115846 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.3921. Min Act: -0.0000

Data Index: 941337 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.5134. Min Act: -0.0000

Data Index: 1516938 (Python Code)

Max Activating Token Index: 172

Text #9

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.2815. Min Act: -0.0000

Data Index: 1186591 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.3353. Min Act: -0.0000

Data Index: 662107 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.3171. Min Act: -0.0000

Data Index: 897668 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.2797. Min Act: -0.0000

Data Index: 728629 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.2392. Min Act: -0.0000

Data Index: 1436769 (Python Code)

Max Activating Token Index: 560

Text #14

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.2144. Min Act: -0.0000

Data Index: 608662 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.1389. Min Act: -0.0000

Data Index: 426416 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.2078. Min Act: -0.0000

Data Index: 1478915 (Python Code)

Max Activating Token Index: 555

Text #17

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.2493. Min Act: -0.0000

Data Index: 1579701 (Python Code)

Max Activating Token Index: 876

Text #18

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.2272. Min Act: -0.0000

Data Index: 1456507 (Python Code)

Max Activating Token Index: 521

Text #19

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.1915. Min Act: -0.0000

Data Index: 1625188 (Python Code)

Max Activating Token Index: 848