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

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

Neuron 4248 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: 1.6467. Min Range: -1.6467

Max Act: 1.6467. Min Act: -0.0000

Data Index: 485093 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.6230. Min Act: -0.0000

Data Index: 428096 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.5037. Min Act: 0.0000

Data Index: 1096053 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3446. Min Act: -0.0000

Data Index: 71535 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.2591. Min Act: -0.0000

Data Index: 759493 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.2221. Min Act: -0.0000

Data Index: 174893 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.1981. Min Act: -0.0000

Data Index: 355708 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.1920. Min Act: -0.0000

Data Index: 54455 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.1825. Min Act: -0.0000

Data Index: 148878 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.1038. Min Act: -0.0000

Data Index: 1327557 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.1694. Min Act: -0.0000

Data Index: 13500 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.0942. Min Act: -0.0000

Data Index: 1147437 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.0914. Min Act: -0.0000

Data Index: 867324 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.0816. Min Act: -0.0000

Data Index: 253510 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.0705. Min Act: -0.0000

Data Index: 5821 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.0626. Min Act: -0.0000

Data Index: 231770 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.0461. Min Act: -0.0000

Data Index: 634491 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.0343. Min Act: -0.0000

Data Index: 648577 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.0254. Min Act: -0.0000

Data Index: 341662 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.0115. Min Act: -0.0000

Data Index: 1353118 (C4 (Web Text))

Max Activating Token Index: 80