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

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

Neuron 3355 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4133. Min Range: -2.4133

Max Act: 2.3452. Min Act: -0.0000

Data Index: 592658 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 2.4133. Min Range: -2.4133

Max Act: 2.4133. Min Act: -0.0000

Data Index: 1060651 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 2.4133. Min Range: -2.4133

Max Act: 2.2096. Min Act: -0.0000

Data Index: 1264246 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 2.4133. Min Range: -2.4133

Max Act: 2.1891. Min Act: -0.0000

Data Index: 513284 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 2.4133. Min Range: -2.4133

Max Act: 2.0296. Min Act: -0.0000

Data Index: 278443 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 2.4133. Min Range: -2.4133

Max Act: 2.0428. Min Act: -0.0000

Data Index: 711331 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 2.4133. Min Range: -2.4133

Max Act: 2.0111. Min Act: -0.0000

Data Index: 396637 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.8970. Min Act: -0.0000

Data Index: 273656 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 2.4133. Min Range: -2.4133

Max Act: 2.1045. Min Act: -0.0000

Data Index: 1319477 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.8271. Min Act: -0.0000

Data Index: 377734 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.9270. Min Act: -0.0000

Data Index: 855933 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.8072. Min Act: -0.0000

Data Index: 69815 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.8518. Min Act: -0.0000

Data Index: 496818 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.8160. Min Act: -0.0000

Data Index: 134922 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.7844. Min Act: -0.0000

Data Index: 637935 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.8009. Min Act: -0.0000

Data Index: 1193475 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.8533. Min Act: -0.0000

Data Index: 452822 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.7576. Min Act: -0.0000

Data Index: 466575 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.7058. Min Act: -0.0000

Data Index: 1142729 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.7269. Min Act: -0.0000

Data Index: 810025 (C4 (Web Text))

Max Activating Token Index: 474