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

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

Neuron 4059 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.8836. Min Act: -0.0001

Data Index: 268288 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6950. Min Act: -0.0001

Data Index: 1213544 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7866. Min Act: -0.0001

Data Index: 563638 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7240. Min Act: -0.0001

Data Index: 384756 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6187. Min Act: -0.0001

Data Index: 1157575 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5836. Min Act: -0.0001

Data Index: 573242 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5798. Min Act: -0.0001

Data Index: 1311868 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5571. Min Act: -0.0001

Data Index: 1180784 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5679. Min Act: -0.0001

Data Index: 649304 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5479. Min Act: -0.0001

Data Index: 632810 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5461. Min Act: -0.0001

Data Index: 322926 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5010. Min Act: -0.0001

Data Index: 480654 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5269. Min Act: -0.0001

Data Index: 550348 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.4893. Min Act: -0.0001

Data Index: 721284 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5744. Min Act: -0.0001

Data Index: 899479 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.4847. Min Act: -0.0001

Data Index: 59778 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.4897. Min Act: -0.0001

Data Index: 1165145 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.4701. Min Act: -0.0001

Data Index: 1290301 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.4996. Min Act: -0.0001

Data Index: 717155 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5269. Min Act: -0.0001

Data Index: 63129 (C4 (Web Text))

Max Activating Token Index: 237