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

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

Neuron 5020 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.4417. Min Act: -0.0000

Data Index: 41568 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1015205 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3975. Min Act: -0.0000

Data Index: 1142357 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1333813 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3754. Min Act: -0.0000

Data Index: 1266574 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3772. Min Act: -0.0000

Data Index: 1266092 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3352. Min Act: -0.0000

Data Index: 1208710 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3170. Min Act: -0.0000

Data Index: 227522 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.2959. Min Act: -0.0000

Data Index: 838217 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3024. Min Act: -0.0000

Data Index: 299814 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.2672. Min Act: -0.0000

Data Index: 793708 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1075166 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.2823. Min Act: -0.0000

Data Index: 983451 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3085. Min Act: -0.0000

Data Index: 996046 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.2725. Min Act: -0.0000

Data Index: 18342 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.2640. Min Act: -0.0000

Data Index: 711525 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.2495. Min Act: -0.0000

Data Index: 555086 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1020733 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1296308 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.2761. Min Act: -0.0000

Data Index: 684917 (C4 (Web Text))

Max Activating Token Index: 512