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

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

Neuron 1405 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: 1.4786. Min Range: -1.4786

Max Act: 1.4786. Min Act: -0.0000

Data Index: 396138 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.3507. Min Act: -0.0000

Data Index: 1167739 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.1594. Min Act: -0.0000

Data Index: 399065 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.2186. Min Act: -0.0000

Data Index: 956222 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.2797. Min Act: -0.0000

Data Index: 892706 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.0549. Min Act: -0.0000

Data Index: 1026752 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.0205. Min Act: -0.0000

Data Index: 581487 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.0164. Min Act: -0.0000

Data Index: 638360 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 1.4786. Min Range: -1.4786

Max Act: 0.9175. Min Act: -0.0000

Data Index: 777620 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 1.4786. Min Range: -1.4786

Max Act: 0.9739. Min Act: -0.0000

Data Index: 615327 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 1.4786. Min Range: -1.4786

Max Act: 0.9668. Min Act: -0.0000

Data Index: 99798 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 1.4786. Min Range: -1.4786

Max Act: 0.9447. Min Act: -0.0000

Data Index: 1313114 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 1.4786. Min Range: -1.4786

Max Act: 0.9683. Min Act: -0.0000

Data Index: 1307978 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 1.4786. Min Range: -1.4786

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1261552 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 1.4786. Min Range: -1.4786

Max Act: 0.9090. Min Act: -0.0000

Data Index: 1064447 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 1.4786. Min Range: -1.4786

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1007928 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 1.4786. Min Range: -1.4786

Max Act: 0.9201. Min Act: -0.0000

Data Index: 867364 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 1.4786. Min Range: -1.4786

Max Act: 0.8751. Min Act: -0.0000

Data Index: 933502 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 1.4786. Min Range: -1.4786

Max Act: 0.9157. Min Act: -0.0000

Data Index: 838712 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 1.4786. Min Range: -1.4786

Max Act: 0.8888. Min Act: -0.0000

Data Index: 188416 (C4 (Web Text))

Max Activating Token Index: 365