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

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

Neuron 3650 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: 2.9811. Min Range: -2.9811

Max Act: 2.9811. Min Act: -0.0000

Data Index: 860756 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 2.9811. Min Range: -2.9811

Max Act: 2.5868. Min Act: -0.0000

Data Index: 391514 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 2.9811. Min Range: -2.9811

Max Act: 2.4233. Min Act: -0.0000

Data Index: 730128 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 2.9811. Min Range: -2.9811

Max Act: 2.4928. Min Act: -0.0000

Data Index: 347314 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 2.9811. Min Range: -2.9811

Max Act: 2.2186. Min Act: -0.0000

Data Index: 423777 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 2.9811. Min Range: -2.9811

Max Act: 2.3137. Min Act: -0.0000

Data Index: 1032656 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 2.9811. Min Range: -2.9811

Max Act: 2.3841. Min Act: -0.0000

Data Index: 945027 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 2.9811. Min Range: -2.9811

Max Act: 2.3553. Min Act: -0.0000

Data Index: 1052264 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 2.9811. Min Range: -2.9811

Max Act: 2.2981. Min Act: -0.0000

Data Index: 123471 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 2.9811. Min Range: -2.9811

Max Act: 2.1716. Min Act: -0.0000

Data Index: 221928 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 2.9811. Min Range: -2.9811

Max Act: 2.2825. Min Act: -0.0000

Data Index: 830700 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 2.9811. Min Range: -2.9811

Max Act: 2.2647. Min Act: -0.0000

Data Index: 717892 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 2.9811. Min Range: -2.9811

Max Act: 2.1298. Min Act: -0.0000

Data Index: 386255 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 2.9811. Min Range: -2.9811

Max Act: 2.1244. Min Act: -0.0000

Data Index: 853749 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 2.9811. Min Range: -2.9811

Max Act: 2.0143. Min Act: -0.0000

Data Index: 397462 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 2.9811. Min Range: -2.9811

Max Act: 2.2172. Min Act: -0.0000

Data Index: 267842 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 2.9811. Min Range: -2.9811

Max Act: 2.1060. Min Act: -0.0000

Data Index: 752644 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 2.9811. Min Range: -2.9811

Max Act: 2.2260. Min Act: -0.0000

Data Index: 247480 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 2.9811. Min Range: -2.9811

Max Act: 2.0951. Min Act: -0.0000

Data Index: 349349 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 2.9811. Min Range: -2.9811

Max Act: 2.2179. Min Act: -0.0000

Data Index: 600884 (C4 (Web Text))

Max Activating Token Index: 938