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

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

Neuron 212 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3162. Min Range: -5.3162

Max Act: 5.3162. Min Act: -0.0000

Data Index: 122796 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 5.3162. Min Range: -5.3162

Max Act: 4.0057. Min Act: -0.0000

Data Index: 221534 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 5.3162. Min Range: -5.3162

Max Act: 3.3781. Min Act: -0.0000

Data Index: 1423272 (Python Code)

Max Activating Token Index: 49

Text #3

Max Range: 5.3162. Min Range: -5.3162

Max Act: 3.3341. Min Act: -0.0000

Data Index: 509611 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 5.3162. Min Range: -5.3162

Max Act: 3.1658. Min Act: -0.0000

Data Index: 1080728 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 5.3162. Min Range: -5.3162

Max Act: 3.1308. Min Act: -0.0000

Data Index: 144784 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 5.3162. Min Range: -5.3162

Max Act: 3.0926. Min Act: -0.0000

Data Index: 97173 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 5.3162. Min Range: -5.3162

Max Act: 3.1977. Min Act: -0.0000

Data Index: 616829 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 5.3162. Min Range: -5.3162

Max Act: 3.1821. Min Act: -0.0000

Data Index: 1325784 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 5.3162. Min Range: -5.3162

Max Act: 2.9753. Min Act: -0.0000

Data Index: 564798 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 5.3162. Min Range: -5.3162

Max Act: 2.4824. Min Act: -0.0000

Data Index: 453112 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 5.3162. Min Range: -5.3162

Max Act: 2.9422. Min Act: -0.0000

Data Index: 553100 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 5.3162. Min Range: -5.3162

Max Act: 3.3641. Min Act: -0.0000

Data Index: 1265908 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 5.3162. Min Range: -5.3162

Max Act: 3.0516. Min Act: -0.0000

Data Index: 771632 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 5.3162. Min Range: -5.3162

Max Act: 2.8733. Min Act: -0.0000

Data Index: 542751 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 5.3162. Min Range: -5.3162

Max Act: 3.1626. Min Act: -0.0000

Data Index: 205666 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 5.3162. Min Range: -5.3162

Max Act: 2.8665. Min Act: -0.0000

Data Index: 480654 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 5.3162. Min Range: -5.3162

Max Act: 3.1467. Min Act: -0.0000

Data Index: 614752 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 5.3162. Min Range: -5.3162

Max Act: 2.8424. Min Act: -0.0000

Data Index: 1528023 (Python Code)

Max Activating Token Index: 117

Text #19

Max Range: 5.3162. Min Range: -5.3162

Max Act: 2.9748. Min Act: -0.0000

Data Index: 921295 (C4 (Web Text))

Max Activating Token Index: 268