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

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

Neuron 5462 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2723. Min Range: -1.2723

Max Act: 1.2602. Min Act: -0.0000

Data Index: 104514 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 1.2723. Min Range: -1.2723

Max Act: 1.2723. Min Act: -0.0000

Data Index: 1170139 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 1.2723. Min Range: -1.2723

Max Act: 1.1710. Min Act: -0.0000

Data Index: 1031342 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 1.2723. Min Range: -1.2723

Max Act: 1.0925. Min Act: -0.0000

Data Index: 1093765 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 1.2723. Min Range: -1.2723

Max Act: 1.0630. Min Act: -0.0000

Data Index: 1312401 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.9712. Min Act: -0.0000

Data Index: 662853 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.9429. Min Act: -0.0000

Data Index: 1003619 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.9337. Min Act: -0.0000

Data Index: 527819 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.9317. Min Act: -0.0000

Data Index: 1019524 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1114311 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.9427. Min Act: -0.0000

Data Index: 379027 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1142896 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.9139. Min Act: -0.0000

Data Index: 132881 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1183812 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.9242. Min Act: -0.0000

Data Index: 402398 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.7758. Min Act: -0.0000

Data Index: 1104481 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.8690. Min Act: -0.0000

Data Index: 857245 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.8629. Min Act: -0.0000

Data Index: 1020212 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.8582. Min Act: -0.0000

Data Index: 790949 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.8513. Min Act: -0.0000

Data Index: 102004 (C4 (Web Text))

Max Activating Token Index: 921