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

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

Neuron 1676 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.5993. Min Act: -0.0000

Data Index: 298725 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.5657. Min Act: -0.0000

Data Index: 967562 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1350363 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.5193. Min Act: -0.0000

Data Index: 1312991 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.5067. Min Act: -0.0000

Data Index: 133022 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.5060. Min Act: -0.0000

Data Index: 401939 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1340195 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4724. Min Act: -0.0000

Data Index: 384780 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1042947 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4631. Min Act: -0.0000

Data Index: 778781 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4213. Min Act: -0.0000

Data Index: 640806 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4095. Min Act: -0.0000

Data Index: 100344 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4393. Min Act: -0.0000

Data Index: 940947 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.3849. Min Act: -0.0000

Data Index: 458528 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.3865. Min Act: -0.0000

Data Index: 501157 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.3992. Min Act: -0.0000

Data Index: 630321 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.3872. Min Act: -0.0000

Data Index: 507485 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.3789. Min Act: -0.0000

Data Index: 449585 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.3825. Min Act: -0.0000

Data Index: 601114 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.3813. Min Act: -0.0000

Data Index: 502465 (C4 (Web Text))

Max Activating Token Index: 933