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

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

Neuron 4572 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4821. Min Range: -2.4821

Max Act: 2.4821. Min Act: -0.0000

Data Index: 1431442 (Python Code)

Max Activating Token Index: 719

Text #1

Max Range: 2.4821. Min Range: -2.4821

Max Act: 2.3960. Min Act: -0.0000

Data Index: 1338289 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 2.4821. Min Range: -2.4821

Max Act: 2.3720. Min Act: -0.0000

Data Index: 1520506 (Python Code)

Max Activating Token Index: 721

Text #3

Max Range: 2.4821. Min Range: -2.4821

Max Act: 2.2853. Min Act: -0.0000

Data Index: 132535 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 2.4821. Min Range: -2.4821

Max Act: 2.2860. Min Act: -0.0000

Data Index: 1372985 (Python Code)

Max Activating Token Index: 737

Text #5

Max Range: 2.4821. Min Range: -2.4821

Max Act: 2.1562. Min Act: -0.0000

Data Index: 1610257 (Python Code)

Max Activating Token Index: 99

Text #6

Max Range: 2.4821. Min Range: -2.4821

Max Act: 2.2139. Min Act: -0.0000

Data Index: 1640111 (Python Code)

Max Activating Token Index: 917

Text #7

Max Range: 2.4821. Min Range: -2.4821

Max Act: 2.2123. Min Act: -0.0000

Data Index: 1405907 (Python Code)

Max Activating Token Index: 1008

Text #8

Max Range: 2.4821. Min Range: -2.4821

Max Act: 2.1696. Min Act: -0.0000

Data Index: 1437791 (Python Code)

Max Activating Token Index: 89

Text #9

Max Range: 2.4821. Min Range: -2.4821

Max Act: 2.2353. Min Act: -0.0000

Data Index: 1547859 (Python Code)

Max Activating Token Index: 553

Text #10

Max Range: 2.4821. Min Range: -2.4821

Max Act: 2.0912. Min Act: -0.0000

Data Index: 626206 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 2.4821. Min Range: -2.4821

Max Act: 2.0192. Min Act: -0.0000

Data Index: 1236817 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 2.4821. Min Range: -2.4821

Max Act: 1.9542. Min Act: -0.0000

Data Index: 180693 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 2.4821. Min Range: -2.4821

Max Act: 2.0262. Min Act: -0.0000

Data Index: 1408760 (Python Code)

Max Activating Token Index: 632

Text #14

Max Range: 2.4821. Min Range: -2.4821

Max Act: 1.8723. Min Act: -0.0000

Data Index: 1418299 (Python Code)

Max Activating Token Index: 276

Text #15

Max Range: 2.4821. Min Range: -2.4821

Max Act: 1.9453. Min Act: -0.0000

Data Index: 753524 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 2.4821. Min Range: -2.4821

Max Act: 1.8423. Min Act: -0.0000

Data Index: 1552810 (Python Code)

Max Activating Token Index: 902

Text #17

Max Range: 2.4821. Min Range: -2.4821

Max Act: 2.0232. Min Act: -0.0000

Data Index: 787157 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 2.4821. Min Range: -2.4821

Max Act: 1.9154. Min Act: -0.0000

Data Index: 1557590 (Python Code)

Max Activating Token Index: 344

Text #19

Max Range: 2.4821. Min Range: -2.4821

Max Act: 1.9014. Min Act: -0.0000

Data Index: 728919 (C4 (Web Text))

Max Activating Token Index: 350