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

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

Neuron 3960 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3405. Min Act: -0.0001

Data Index: 524494 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3584. Min Act: -0.0001

Data Index: 165898 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3072. Min Act: -0.0001

Data Index: 659964 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3384. Min Act: -0.0001

Data Index: 307806 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3355. Min Act: -0.0001

Data Index: 1649760 (Python Code)

Max Activating Token Index: 312

Text #5

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3319. Min Act: -0.0001

Data Index: 1342273 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3124. Min Act: -0.0000

Data Index: 1039079 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3099. Min Act: -0.0001

Data Index: 378971 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2984. Min Act: -0.0001

Data Index: 408987 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3003. Min Act: -0.0001

Data Index: 1330464 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2652. Min Act: -0.0001

Data Index: 45826 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2891. Min Act: -0.0001

Data Index: 1334307 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3027. Min Act: -0.0001

Data Index: 65165 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2830. Min Act: -0.0001

Data Index: 970164 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2618. Min Act: -0.0001

Data Index: 1431855 (Python Code)

Max Activating Token Index: 154

Text #15

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2840. Min Act: -0.0001

Data Index: 775076 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2788. Min Act: -0.0001

Data Index: 328096 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2879. Min Act: -0.0001

Data Index: 286167 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2697. Min Act: -0.0001

Data Index: 923744 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2433. Min Act: -0.0001

Data Index: 95536 (C4 (Web Text))

Max Activating Token Index: 788