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

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

Neuron 2809 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3829. Min Range: -3.3829

Max Act: 3.3829. Min Act: -0.0000

Data Index: 1551982 (Python Code)

Max Activating Token Index: 49

Text #1

Max Range: 3.3829. Min Range: -3.3829

Max Act: 2.9826. Min Act: -0.0000

Data Index: 1525961 (Python Code)

Max Activating Token Index: 838

Text #2

Max Range: 3.3829. Min Range: -3.3829

Max Act: 3.1203. Min Act: -0.0000

Data Index: 262106 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 3.3829. Min Range: -3.3829

Max Act: 2.9325. Min Act: -0.0000

Data Index: 618597 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 3.3829. Min Range: -3.3829

Max Act: 2.9321. Min Act: -0.0000

Data Index: 1365280 (Python Code)

Max Activating Token Index: 134

Text #5

Max Range: 3.3829. Min Range: -3.3829

Max Act: 2.9121. Min Act: -0.0000

Data Index: 1411595 (Python Code)

Max Activating Token Index: 617

Text #6

Max Range: 3.3829. Min Range: -3.3829

Max Act: 2.7184. Min Act: -0.0000

Data Index: 340871 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 3.3829. Min Range: -3.3829

Max Act: 2.7137. Min Act: -0.0000

Data Index: 975567 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 3.3829. Min Range: -3.3829

Max Act: 2.8261. Min Act: -0.0000

Data Index: 1525281 (Python Code)

Max Activating Token Index: 924

Text #9

Max Range: 3.3829. Min Range: -3.3829

Max Act: 2.8031. Min Act: -0.0000

Data Index: 1503208 (Python Code)

Max Activating Token Index: 964

Text #10

Max Range: 3.3829. Min Range: -3.3829

Max Act: 2.8048. Min Act: -0.0000

Data Index: 358923 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 3.3829. Min Range: -3.3829

Max Act: 2.9097. Min Act: -0.0000

Data Index: 332461 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 3.3829. Min Range: -3.3829

Max Act: 2.6986. Min Act: -0.0000

Data Index: 272684 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 3.3829. Min Range: -3.3829

Max Act: 2.7081. Min Act: -0.0000

Data Index: 1641509 (Python Code)

Max Activating Token Index: 380

Text #14

Max Range: 3.3829. Min Range: -3.3829

Max Act: 2.6752. Min Act: -0.0000

Data Index: 1295750 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 3.3829. Min Range: -3.3829

Max Act: 2.5434. Min Act: -0.0000

Data Index: 1159606 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 3.3829. Min Range: -3.3829

Max Act: 2.6509. Min Act: -0.0000

Data Index: 306350 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 3.3829. Min Range: -3.3829

Max Act: 2.2832. Min Act: -0.0000

Data Index: 1102771 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 3.3829. Min Range: -3.3829

Max Act: 2.9146. Min Act: -0.0000

Data Index: 698712 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 3.3829. Min Range: -3.3829

Max Act: 2.6256. Min Act: -0.0000

Data Index: 175602 (C4 (Web Text))

Max Activating Token Index: 182