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

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

Neuron 1663 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.6966. Min Act: -0.0000

Data Index: 112658 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.5405. Min Act: -0.0000

Data Index: 840149 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.5993. Min Act: -0.0000

Data Index: 1192318 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.4968. Min Act: -0.0001

Data Index: 734002 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.4894. Min Act: -0.0000

Data Index: 6443 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.4368. Min Act: -0.0000

Data Index: 952907 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.3588. Min Act: -0.0001

Data Index: 446900 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.1962. Min Act: -0.0000

Data Index: 289476 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.3286. Min Act: -0.0000

Data Index: 1166804 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2723. Min Act: -0.0000

Data Index: 440816 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2328. Min Act: -0.0000

Data Index: 725501 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2670. Min Act: -0.0000

Data Index: 192567 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2207. Min Act: -0.0000

Data Index: 164437 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2046. Min Act: -0.0000

Data Index: 953109 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.1722. Min Act: -0.0000

Data Index: 421218 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.1774. Min Act: -0.0000

Data Index: 1042594 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.1782. Min Act: -0.0000

Data Index: 982210 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2765. Min Act: -0.0000

Data Index: 804601 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.1511. Min Act: -0.0000

Data Index: 801580 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.1167. Min Act: -0.0000

Data Index: 1272177 (C4 (Web Text))

Max Activating Token Index: 482