Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1728 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.8585. Min Act: -0.0000

Data Index: 1068209 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.7303. Min Act: -0.0000

Data Index: 946988 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.5650. Min Act: -0.0000

Data Index: 53928 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.3004. Min Act: -0.0000

Data Index: 278727 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.3993. Min Act: -0.0000

Data Index: 448040 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.4801. Min Act: -0.0000

Data Index: 1253309 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.2127. Min Act: -0.0000

Data Index: 581760 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.3493. Min Act: -0.0000

Data Index: 919307 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.2682. Min Act: -0.0000

Data Index: 12255 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.3888. Min Act: -0.0000

Data Index: 39557 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.2637. Min Act: -0.0000

Data Index: 641666 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.0984. Min Act: -0.0000

Data Index: 823223 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.1212. Min Act: -0.0000

Data Index: 699616 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.1267. Min Act: -0.0000

Data Index: 908176 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.3028. Min Act: -0.0000

Data Index: 850643 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.1585. Min Act: -0.0000

Data Index: 429461 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.1670. Min Act: -0.0000

Data Index: 191683 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.1157. Min Act: -0.0000

Data Index: 945234 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.2277. Min Act: -0.0000

Data Index: 995676 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 2.8585. Min Range: -2.8585

Max Act: 2.0852. Min Act: -0.0000

Data Index: 1352673 (C4 (Web Text))

Max Activating Token Index: 165