Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3423 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0845. Min Range: -1.0845

Max Act: 1.0597. Min Act: -0.0000

Data Index: 306331 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 1.0845. Min Range: -1.0845

Max Act: 1.0845. Min Act: -0.0000

Data Index: 533985 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 1.0845. Min Range: -1.0845

Max Act: 1.0083. Min Act: -0.0000

Data Index: 533729 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 1.0845. Min Range: -1.0845

Max Act: 0.9774. Min Act: -0.0000

Data Index: 288832 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 1.0845. Min Range: -1.0845

Max Act: 1.0013. Min Act: -0.0000

Data Index: 235812 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 1.0845. Min Range: -1.0845

Max Act: 1.0019. Min Act: -0.0000

Data Index: 728575 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 1.0845. Min Range: -1.0845

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1157621 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 1.0845. Min Range: -1.0845

Max Act: 0.9677. Min Act: -0.0000

Data Index: 537950 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 1.0845. Min Range: -1.0845

Max Act: 0.8992. Min Act: -0.0000

Data Index: 1199232 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 1.0845. Min Range: -1.0845

Max Act: 0.8710. Min Act: -0.0000

Data Index: 873905 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 1.0845. Min Range: -1.0845

Max Act: 0.9277. Min Act: -0.0000

Data Index: 615384 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 1.0845. Min Range: -1.0845

Max Act: 0.8922. Min Act: -0.0000

Data Index: 1118376 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 1.0845. Min Range: -1.0845

Max Act: 0.8891. Min Act: -0.0000

Data Index: 1354707 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 1.0845. Min Range: -1.0845

Max Act: 0.8639. Min Act: -0.0000

Data Index: 685131 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 1.0845. Min Range: -1.0845

Max Act: 0.8614. Min Act: -0.0000

Data Index: 755642 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 1.0845. Min Range: -1.0845

Max Act: 0.8713. Min Act: -0.0000

Data Index: 1284503 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 1.0845. Min Range: -1.0845

Max Act: 0.9407. Min Act: -0.0000

Data Index: 422295 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 1.0845. Min Range: -1.0845

Max Act: 0.8533. Min Act: -0.0000

Data Index: 783222 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 1.0845. Min Range: -1.0845

Max Act: 0.8598. Min Act: -0.0000

Data Index: 735000 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 1.0845. Min Range: -1.0845

Max Act: 0.8023. Min Act: -0.0000

Data Index: 268763 (C4 (Web Text))

Max Activating Token Index: 301