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

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

Neuron 4623 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3463. Min Range: -1.3463

Max Act: 1.3463. Min Act: -0.0000

Data Index: 782242 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 1.3463. Min Range: -1.3463

Max Act: 1.2644. Min Act: 0.0000

Data Index: 581340 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1155774 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.9676. Min Act: 0.0001

Data Index: 1323921 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.8860. Min Act: -0.0000

Data Index: 218101 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.8770. Min Act: -0.0000

Data Index: 410213 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.8582. Min Act: -0.0000

Data Index: 844831 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.8521. Min Act: -0.0000

Data Index: 45161 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.8966. Min Act: -0.0000

Data Index: 392762 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.8197. Min Act: -0.0000

Data Index: 673037 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.8048. Min Act: -0.0000

Data Index: 81088 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.8058. Min Act: 0.0000

Data Index: 719252 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.8046. Min Act: 0.0000

Data Index: 684728 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.8035. Min Act: -0.0000

Data Index: 1239500 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.7736. Min Act: -0.0000

Data Index: 570697 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.7835. Min Act: -0.0000

Data Index: 429058 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.7880. Min Act: 0.0000

Data Index: 323676 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.7354. Min Act: -0.0000

Data Index: 243044 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.7797. Min Act: -0.0000

Data Index: 937951 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.7756. Min Act: -0.0000

Data Index: 82078 (C4 (Web Text))

Max Activating Token Index: 192