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

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

Neuron 4763 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: 1.4918. Min Range: -1.4918

Max Act: 1.4918. Min Act: -0.0000

Data Index: 1276438 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 1.4918. Min Range: -1.4918

Max Act: 0.8607. Min Act: -0.0000

Data Index: 12730 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 1.4918. Min Range: -1.4918

Max Act: 0.9058. Min Act: -0.0000

Data Index: 278147 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 1.4918. Min Range: -1.4918

Max Act: 0.8882. Min Act: -0.0000

Data Index: 1227435 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 1.4918. Min Range: -1.4918

Max Act: 0.8910. Min Act: -0.0000

Data Index: 450366 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 1.4918. Min Range: -1.4918

Max Act: 0.8183. Min Act: -0.0000

Data Index: 722492 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 1.4918. Min Range: -1.4918

Max Act: 0.7986. Min Act: -0.0000

Data Index: 1309189 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 1.4918. Min Range: -1.4918

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1266451 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 1.4918. Min Range: -1.4918

Max Act: 0.7848. Min Act: -0.0000

Data Index: 1347193 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 1.4918. Min Range: -1.4918

Max Act: 0.7304. Min Act: -0.0000

Data Index: 693336 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 1.4918. Min Range: -1.4918

Max Act: 0.7350. Min Act: -0.0000

Data Index: 19556 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 1.4918. Min Range: -1.4918

Max Act: 0.7286. Min Act: -0.0000

Data Index: 844292 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 1.4918. Min Range: -1.4918

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1226257 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 1.4918. Min Range: -1.4918

Max Act: 0.6604. Min Act: -0.0000

Data Index: 28880 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 1.4918. Min Range: -1.4918

Max Act: 0.6593. Min Act: -0.0000

Data Index: 851422 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 1.4918. Min Range: -1.4918

Max Act: 0.6527. Min Act: -0.0000

Data Index: 585831 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 1.4918. Min Range: -1.4918

Max Act: 0.6498. Min Act: -0.0000

Data Index: 330974 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 1.4918. Min Range: -1.4918

Max Act: 0.6413. Min Act: -0.0000

Data Index: 930269 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 1.4918. Min Range: -1.4918

Max Act: 0.6442. Min Act: -0.0000

Data Index: 869432 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 1.4918. Min Range: -1.4918

Max Act: 0.6377. Min Act: -0.0000

Data Index: 162751 (C4 (Web Text))

Max Activating Token Index: 970