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

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

Neuron 308 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.6661. Min Act: 0.0000

Data Index: 311996 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1273154 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5136. Min Act: -0.0000

Data Index: 175171 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.5082. Min Act: -0.0000

Data Index: 742978 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.4796. Min Act: -0.0000

Data Index: 332588 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.4499. Min Act: 0.0000

Data Index: 1282230 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.4396. Min Act: -0.0000

Data Index: 806001 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.4117. Min Act: -0.0000

Data Index: 961101 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.4067. Min Act: -0.0000

Data Index: 102571 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.4163. Min Act: -0.0000

Data Index: 309070 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.4106. Min Act: -0.0000

Data Index: 49900 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.3787. Min Act: -0.0000

Data Index: 1281761 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.3772. Min Act: -0.0000

Data Index: 936365 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.3776. Min Act: -0.0000

Data Index: 872841 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.3593. Min Act: -0.0000

Data Index: 346331 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.3400. Min Act: -0.0000

Data Index: 904331 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.3570. Min Act: -0.0000

Data Index: 151729 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.3460. Min Act: -0.0000

Data Index: 125327 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.3278. Min Act: -0.0000

Data Index: 763155 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.6661. Min Range: -0.6661

Max Act: 0.3407. Min Act: -0.0000

Data Index: 815024 (C4 (Web Text))

Max Activating Token Index: 838