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

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

Neuron 2116 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: 0.6955. Min Range: -0.6955

Max Act: 0.6955. Min Act: -0.0000

Data Index: 91078 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5821. Min Act: -0.0000

Data Index: 557133 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5928. Min Act: -0.0000

Data Index: 810584 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5946. Min Act: -0.0000

Data Index: 1253849 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5728. Min Act: -0.0000

Data Index: 415085 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5809. Min Act: -0.0000

Data Index: 1198257 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5801. Min Act: -0.0000

Data Index: 903375 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1338535 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1344662 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5424. Min Act: -0.0000

Data Index: 590833 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5824. Min Act: -0.0000

Data Index: 1289205 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5338. Min Act: -0.0000

Data Index: 630251 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1151766 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5363. Min Act: -0.0000

Data Index: 380365 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5259. Min Act: -0.0000

Data Index: 430976 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5159. Min Act: -0.0000

Data Index: 360064 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1230504 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5025. Min Act: -0.0000

Data Index: 668110 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5374. Min Act: -0.0000

Data Index: 536239 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1273384 (C4 (Web Text))

Max Activating Token Index: 922