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

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

Neuron 4356 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.3241. Min Act: -0.0002

Data Index: 222476 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.3122. Min Act: -0.0002

Data Index: 528478 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.3129. Min Act: -0.0002

Data Index: 1358829 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.3114. Min Act: -0.0002

Data Index: 526362 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.3100. Min Act: -0.0002

Data Index: 1314831 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.3073. Min Act: -0.0002

Data Index: 771086 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.3045. Min Act: -0.0002

Data Index: 496474 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.3042. Min Act: -0.0002

Data Index: 142660 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.3017. Min Act: -0.0002

Data Index: 702354 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.3019. Min Act: -0.0002

Data Index: 1165187 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.3009. Min Act: -0.0002

Data Index: 25136 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.2997. Min Act: -0.0002

Data Index: 117123 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.2991. Min Act: -0.0002

Data Index: 189426 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.2984. Min Act: -0.0002

Data Index: 84313 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.2881. Min Act: -0.0002

Data Index: 684334 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.2993. Min Act: -0.0002

Data Index: 429836 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.2866. Min Act: -0.0002

Data Index: 667315 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.2966. Min Act: -0.0002

Data Index: 63335 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.2870. Min Act: -0.0002

Data Index: 482389 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.3241. Min Range: -0.3241

Max Act: 0.2968. Min Act: -0.0002

Data Index: 1178973 (C4 (Web Text))

Max Activating Token Index: 8