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

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

Neuron 561 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1190. Min Range: -1.1190

Max Act: 1.1190. Min Act: -0.0000

Data Index: 221516 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 1.1190. Min Range: -1.1190

Max Act: 1.0274. Min Act: -0.0000

Data Index: 885333 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 1.1190. Min Range: -1.1190

Max Act: 1.0675. Min Act: -0.0000

Data Index: 975951 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 1.1190. Min Range: -1.1190

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1111252 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 1.1190. Min Range: -1.1190

Max Act: 1.0194. Min Act: -0.0000

Data Index: 1160006 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 1.1190. Min Range: -1.1190

Max Act: 1.0488. Min Act: -0.0000

Data Index: 1147445 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 1.1190. Min Range: -1.1190

Max Act: 0.9860. Min Act: -0.0000

Data Index: 392545 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 1.1190. Min Range: -1.1190

Max Act: 0.9534. Min Act: -0.0000

Data Index: 1026375 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 1.1190. Min Range: -1.1190

Max Act: 0.9835. Min Act: -0.0000

Data Index: 565576 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 1.1190. Min Range: -1.1190

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1104432 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 1.1190. Min Range: -1.1190

Max Act: 0.9638. Min Act: -0.0000

Data Index: 456212 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 1.1190. Min Range: -1.1190

Max Act: 0.9738. Min Act: -0.0000

Data Index: 760689 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 1.1190. Min Range: -1.1190

Max Act: 0.9478. Min Act: -0.0000

Data Index: 967152 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 1.1190. Min Range: -1.1190

Max Act: 0.9384. Min Act: -0.0000

Data Index: 845863 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 1.1190. Min Range: -1.1190

Max Act: 0.9016. Min Act: -0.0000

Data Index: 1091708 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 1.1190. Min Range: -1.1190

Max Act: 0.9597. Min Act: -0.0000

Data Index: 309025 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 1.1190. Min Range: -1.1190

Max Act: 0.9262. Min Act: -0.0000

Data Index: 29938 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 1.1190. Min Range: -1.1190

Max Act: 0.9300. Min Act: -0.0000

Data Index: 1136502 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 1.1190. Min Range: -1.1190

Max Act: 0.8993. Min Act: -0.0000

Data Index: 72391 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 1.1190. Min Range: -1.1190

Max Act: 0.8916. Min Act: -0.0000

Data Index: 347943 (C4 (Web Text))

Max Activating Token Index: 422