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

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

Neuron 2502 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: 0.9467. Min Range: -0.9467

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1110500 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.8352. Min Act: -0.0001

Data Index: 327760 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.7176. Min Act: -0.0000

Data Index: 403417 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.7759. Min Act: -0.0000

Data Index: 85399 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.7214. Min Act: -0.0000

Data Index: 414398 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6657. Min Act: -0.0000

Data Index: 446537 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.7005. Min Act: -0.0000

Data Index: 1186979 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1028410 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6561. Min Act: -0.0000

Data Index: 178280 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6993. Min Act: -0.0001

Data Index: 1172956 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6521. Min Act: -0.0000

Data Index: 918094 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6140. Min Act: -0.0000

Data Index: 892332 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6374. Min Act: -0.0000

Data Index: 739924 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6111. Min Act: -0.0000

Data Index: 422027 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6220. Min Act: -0.0000

Data Index: 741135 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6437. Min Act: -0.0000

Data Index: 653256 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.5585. Min Act: -0.0001

Data Index: 392586 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1265787 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6748. Min Act: -0.0000

Data Index: 216538 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.5927. Min Act: -0.0000

Data Index: 372481 (C4 (Web Text))

Max Activating Token Index: 77