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

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

Neuron 3637 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: 4.8254. Min Range: -4.8254

Max Act: 4.8254. Min Act: -0.0000

Data Index: 84983 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 4.8254. Min Range: -4.8254

Max Act: 4.6347. Min Act: -0.0000

Data Index: 1092476 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 4.8254. Min Range: -4.8254

Max Act: 4.0130. Min Act: -0.0000

Data Index: 1026561 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 4.8254. Min Range: -4.8254

Max Act: 4.2627. Min Act: -0.0000

Data Index: 1140596 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 4.8254. Min Range: -4.8254

Max Act: 4.2451. Min Act: -0.0000

Data Index: 1239136 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 4.8254. Min Range: -4.8254

Max Act: 4.0366. Min Act: -0.0000

Data Index: 596428 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 4.8254. Min Range: -4.8254

Max Act: 4.2081. Min Act: -0.0000

Data Index: 1107898 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 4.8254. Min Range: -4.8254

Max Act: 4.3494. Min Act: -0.0000

Data Index: 929980 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 4.8254. Min Range: -4.8254

Max Act: 4.1927. Min Act: -0.0000

Data Index: 514858 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 4.8254. Min Range: -4.8254

Max Act: 4.3075. Min Act: -0.0000

Data Index: 446100 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 4.8254. Min Range: -4.8254

Max Act: 3.9517. Min Act: -0.0000

Data Index: 1356319 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 4.8254. Min Range: -4.8254

Max Act: 3.9270. Min Act: -0.0000

Data Index: 531351 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 4.8254. Min Range: -4.8254

Max Act: 4.0310. Min Act: -0.0000

Data Index: 421125 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 4.8254. Min Range: -4.8254

Max Act: 4.1819. Min Act: -0.0000

Data Index: 611203 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 4.8254. Min Range: -4.8254

Max Act: 3.9760. Min Act: -0.0000

Data Index: 757230 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 4.8254. Min Range: -4.8254

Max Act: 3.7755. Min Act: -0.0000

Data Index: 247749 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 4.8254. Min Range: -4.8254

Max Act: 3.9234. Min Act: -0.0000

Data Index: 517123 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 4.8254. Min Range: -4.8254

Max Act: 4.0679. Min Act: -0.0000

Data Index: 981029 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 4.8254. Min Range: -4.8254

Max Act: 3.8892. Min Act: -0.0000

Data Index: 1097411 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 4.8254. Min Range: -4.8254

Max Act: 3.8558. Min Act: -0.0000

Data Index: 674121 (C4 (Web Text))

Max Activating Token Index: 102