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

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

Neuron 3566 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.8710. Min Act: -0.0000

Data Index: 1314201 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.7799. Min Act: -0.0000

Data Index: 343233 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.3192. Min Act: -0.0000

Data Index: 1083007 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.5489. Min Act: -0.0000

Data Index: 1355936 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.3535. Min Act: -0.0000

Data Index: 994450 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.2671. Min Act: -0.0000

Data Index: 1006317 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.4132. Min Act: -0.0000

Data Index: 116461 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.3014. Min Act: -0.0000

Data Index: 569314 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.2619. Min Act: -0.0000

Data Index: 1307578 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.0961. Min Act: -0.0000

Data Index: 650335 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.1648. Min Act: -0.0000

Data Index: 551857 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.0273. Min Act: -0.0000

Data Index: 1325327 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.1550. Min Act: -0.0000

Data Index: 724998 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.3269. Min Act: -0.0000

Data Index: 388042 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.2576. Min Act: -0.0000

Data Index: 157210 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.2057. Min Act: -0.0000

Data Index: 793138 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.2594. Min Act: -0.0000

Data Index: 593761 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.0035. Min Act: -0.0000

Data Index: 636262 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.1208. Min Act: -0.0000

Data Index: 82123 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.2277. Min Act: -0.0000

Data Index: 837081 (C4 (Web Text))

Max Activating Token Index: 664