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

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

Neuron 4690 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: 0.7563. Min Range: -0.7563

Max Act: 0.7563. Min Act: -0.0000

Data Index: 667006 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6969. Min Act: -0.0000

Data Index: 719863 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6571. Min Act: -0.0000

Data Index: 400096 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6304. Min Act: -0.0000

Data Index: 241053 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6087. Min Act: -0.0000

Data Index: 4594 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6071. Min Act: -0.0000

Data Index: 362786 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5539. Min Act: -0.0000

Data Index: 55970 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5876. Min Act: -0.0000

Data Index: 448070 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5966. Min Act: -0.0000

Data Index: 164721 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5865. Min Act: -0.0000

Data Index: 1351064 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5490. Min Act: -0.0000

Data Index: 984997 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1205813 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.4814. Min Act: -0.0000

Data Index: 195983 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5068. Min Act: -0.0000

Data Index: 925423 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.4988. Min Act: -0.0000

Data Index: 406083 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5032. Min Act: -0.0000

Data Index: 1049294 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5227. Min Act: -0.0000

Data Index: 878082 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5044. Min Act: -0.0000

Data Index: 437294 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5074. Min Act: -0.0000

Data Index: 991282 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5314. Min Act: -0.0000

Data Index: 888210 (C4 (Web Text))

Max Activating Token Index: 1002