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

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

Neuron 4520 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4913. Min Act: -0.0000

Data Index: 879145 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1050082 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4984. Min Act: -0.0000

Data Index: 938847 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4803. Min Act: -0.0000

Data Index: 194850 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4755. Min Act: -0.0000

Data Index: 121440 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4741. Min Act: -0.0000

Data Index: 961452 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.5003. Min Act: -0.0000

Data Index: 665160 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4264. Min Act: -0.0000

Data Index: 449374 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4336. Min Act: -0.0000

Data Index: 198745 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1100593 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4283. Min Act: -0.0000

Data Index: 636944 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4159. Min Act: -0.0000

Data Index: 375458 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4094. Min Act: -0.0000

Data Index: 1076739 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4074. Min Act: -0.0000

Data Index: 218701 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1101086 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3912. Min Act: -0.0000

Data Index: 964788 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1243003 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4383. Min Act: -0.0000

Data Index: 590481 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3514. Min Act: -0.0000

Data Index: 598724 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3640. Min Act: -0.0000

Data Index: 657570 (C4 (Web Text))

Max Activating Token Index: 31