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

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

Neuron 23 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4015. Min Range: -2.4015

Max Act: 2.4015. Min Act: -0.0000

Data Index: 69444 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 2.4015. Min Range: -2.4015

Max Act: 2.0690. Min Act: -0.0000

Data Index: 379940 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.8266. Min Act: -0.0000

Data Index: 1284638 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.9051. Min Act: -0.0000

Data Index: 299804 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.6373. Min Act: -0.0000

Data Index: 83794 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.5840. Min Act: -0.0000

Data Index: 1185683 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.5751. Min Act: -0.0000

Data Index: 384475 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.4236. Min Act: -0.0000

Data Index: 1065465 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.3318. Min Act: -0.0000

Data Index: 52676 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.3894. Min Act: -0.0000

Data Index: 1273747 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.1814. Min Act: -0.0000

Data Index: 1260441 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.3915. Min Act: -0.0000

Data Index: 1231110 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.2185. Min Act: -0.0000

Data Index: 54477 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.3765. Min Act: -0.0000

Data Index: 954462 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.3412. Min Act: -0.0000

Data Index: 456166 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.2592. Min Act: -0.0000

Data Index: 742999 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.1737. Min Act: -0.0000

Data Index: 389042 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.2566. Min Act: -0.0000

Data Index: 1250376 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.1637. Min Act: -0.0000

Data Index: 1111292 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.2415. Min Act: -0.0000

Data Index: 881139 (C4 (Web Text))

Max Activating Token Index: 397