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

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

Neuron 2101 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.7220. Min Act: -0.0000

Data Index: 1197303 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.8069. Min Act: -0.0000

Data Index: 972277 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.6900. Min Act: -0.0000

Data Index: 33249 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.6136. Min Act: -0.0000

Data Index: 360263 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.5996. Min Act: -0.0000

Data Index: 1008745 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.5817. Min Act: -0.0000

Data Index: 1271166 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.5019. Min Act: -0.0000

Data Index: 1128174 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.4581. Min Act: -0.0000

Data Index: 696415 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.4510. Min Act: -0.0000

Data Index: 116435 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.4177. Min Act: -0.0000

Data Index: 15241 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.2683. Min Act: -0.0000

Data Index: 56214 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.3688. Min Act: -0.0000

Data Index: 1159823 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.3309. Min Act: -0.0000

Data Index: 1275842 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.3197. Min Act: -0.0000

Data Index: 606368 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.3040. Min Act: -0.0000

Data Index: 1090841 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.3120. Min Act: -0.0000

Data Index: 113199 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.2873. Min Act: -0.0000

Data Index: 187119 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.2864. Min Act: -0.0000

Data Index: 850286 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.2823. Min Act: 0.0000

Data Index: 678549 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.2696. Min Act: -0.0000

Data Index: 554244 (C4 (Web Text))

Max Activating Token Index: 291