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

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

Neuron 512 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: 0.5887. Min Range: -0.5887

Max Act: 0.5887. Min Act: 0.0000

Data Index: 992696 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.5053. Min Act: -0.0000

Data Index: 363778 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.5003. Min Act: -0.0000

Data Index: 685152 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.5135. Min Act: -0.0000

Data Index: 756140 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4888. Min Act: -0.0000

Data Index: 132426 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4488. Min Act: -0.0000

Data Index: 480715 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4509. Min Act: -0.0000

Data Index: 991737 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4815. Min Act: -0.0000

Data Index: 176191 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4468. Min Act: -0.0000

Data Index: 504859 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4490. Min Act: -0.0000

Data Index: 1124207 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4314. Min Act: -0.0000

Data Index: 399666 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3971. Min Act: -0.0000

Data Index: 342753 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4080. Min Act: -0.0000

Data Index: 1069998 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4214. Min Act: -0.0000

Data Index: 1142919 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4022. Min Act: -0.0000

Data Index: 515955 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1200856 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4014. Min Act: -0.0000

Data Index: 862799 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3805. Min Act: -0.0000

Data Index: 767375 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3903. Min Act: -0.0000

Data Index: 176130 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4199. Min Act: -0.0000

Data Index: 40452 (C4 (Web Text))

Max Activating Token Index: 844