Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3132 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.7544. Min Act: -0.0000

Data Index: 1344611 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.6979. Min Act: -0.0000

Data Index: 345524 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.6281. Min Act: -0.0000

Data Index: 713591 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.6835. Min Act: -0.0000

Data Index: 1074186 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.6791. Min Act: -0.0000

Data Index: 411076 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.5747. Min Act: -0.0000

Data Index: 706274 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.4023. Min Act: -0.0000

Data Index: 614010 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.3950. Min Act: -0.0000

Data Index: 1102796 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.3943. Min Act: -0.0000

Data Index: 943148 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.3792. Min Act: -0.0000

Data Index: 1307137 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.3566. Min Act: -0.0000

Data Index: 427813 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.3311. Min Act: -0.0000

Data Index: 1247985 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.2361. Min Act: -0.0000

Data Index: 193885 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.2913. Min Act: -0.0000

Data Index: 441074 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.3047. Min Act: -0.0000

Data Index: 1267758 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.2157. Min Act: -0.0000

Data Index: 862094 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.2827. Min Act: -0.0000

Data Index: 212175 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.2449. Min Act: -0.0000

Data Index: 828059 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.2333. Min Act: -0.0000

Data Index: 1048570 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 1.7544. Min Range: -1.7544

Max Act: 1.2332. Min Act: -0.0000

Data Index: 330252 (C4 (Web Text))

Max Activating Token Index: 85